Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover read-only/idempotent, but the description adds material context beyond them: the query is not logged or written back, test records are excluded unless is_test is true, matches are unverified, and sensitive data must not be submitted. For a privacy-sensitive read tool this is exactly the disclosure an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly five sentences, all front-loaded, beginning with the core purpose before privacy and reliability caveats. Every sentence carries information (matching guidance, safety warning, expectation setting), though the privacy sentence is dense and could be slightly tightened.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description accordingly sets expectations about returns: there may be no relevant match, learned observations are unverified, and test records are filtered. Combined with the input guidance, an agent has everything needed to call this correctly and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 50% – 'tried' and 'blocker' have no schema descriptions – but the description compensates by explaining both are optional descriptions of the current blocker and approaches already tried. It also clarifies the is_test exclusion behavior. It does not add length or format detail beyond the schema, so it falls just short of a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (search) and resource (shared MAGNT memory / contributed task signals) and ties it to the current task. It is clearly the read counterpart to the sibling contribute_task_signal, and the 'read-only: your query is not added to shared memory' line sharpens that contrast.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context for use: describe the outcome you are currently trying to achieve, optionally add a blocker and approaches tried. It also pre-empts misuse by warning the memory is experimental, may return nothing, and that a similar task is not proof of a solution. It stops short of explicitly naming when to prefer a sibling such as contribute_task_signal, so it is strong but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.