Trust and verification

Pattern set

The versioned list of rules this site uses to read MCP tool descriptions for instructions that do not belong there.

Each rule is published with the weakness it is an instance of, an example it catches, the honest sentence nearest to it that it must leave alone, and a count, taken by hand across the catalogue, of how often it has been right and wrong.

A released set is never edited. Changing a rule makes a new version, and every listing records which version it was read with, so a result can always be traced to the exact rules that produced it.

Why it matters

It is what the tool description integrity row of the rubric is answered with, and publishing it is what lets anybody check the answer.

The mistake everyone makes

Assuming a rule set is better for having more rules. A rule nobody has counted is a guess, and on this site it ships switched off.

Related terms

Tool poisoning

Hiding instructions inside a tool description so the model reads them as commands.

Tool description

The text an MCP server publishes about each of its tools, which the model reads to decide what to call and how.

False positive

A finding that is not real: the check matched something that is not the problem it looks for.

Rubric

The versioned list of checks verification runs, published in full.

See Pattern set on a real listing

Every term here shows up in the catalogue next to a real result, with the findings published and the limits stated. Free to browse, no account needed.

Open the catalogue