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

Annotations only declare readOnlyHint=true, so the description carries real added weight: it discloses scoping (this user only), cost profile, and the acceptability of an empty result set. It further warns that memories are historical reports rather than current selection authority, and that current state must be verified through owning tools — a non-obvious caveat about how to interpret output.

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?

Purpose is front-loaded in the first line, followed by a scannable trigger list and a short caveat paragraph — no filler. The closing passage on selection authority is somewhat discursive relative to the invocation decision, keeping it just below top marks.

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?

For a 3-parameter read tool with a readOnly annotation and no output schema, the definition covers when to call, cost, scope, and how to treat results. Return shape is only described incidentally inside the `query` schema text, and there is no guidance on choosing `limit` or on filter key conventions, leaving a small gap.

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 description coverage is 100%, with the `query` parameter already documenting examples and ordering, and `filters` documenting its metadata-tag behavior. The description adds only an oblique hint about discovery ('without a remembered-name filter'); it says nothing about `limit` tuning or query phrasing beyond the schema, so baseline 3 applies.

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 and resource — 'Retrieve relevant prior memories about this user' — with scope (this user only) made explicit. It does not, however, distinguish itself from the close siblings `search_conversation_history` and `remember`, which an agent must otherwise infer from the resource word alone.

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 concrete triggering conditions in a bullet list (past-context references, preference-sensitive advice, trading problems, anything possibly recorded) plus an explicit default policy: 'Default to calling this tool more often than you think you should.' It also pre-empts the main hesitation by noting the call is cheap and zero results are fine.

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