Recall

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

Annotations only declare readOnlyHint=true, so the description carries most of the burden and does add real value: the search mechanism, the no-query fallback behavior, and the meaning of the STALE flag in results. It omits anything about result shape beyond the STALE flag or any token-cost behavior implied by max_tokens, which is a modest gap.

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?

Three short sentences, each earning its place: purpose, when to call, fallback behavior, and result semantics. Front-loaded with the core action and free of filler.

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?

No output schema exists, and the description compensates by explaining the STALE flag, which is the one non-obvious part of the return. Combined with the readOnly annotation, an agent has enough to call this safely; the remaining gap is the undocumented kind and limit parameters.

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 only 25%, so the description must compensate, and it only covers one of four parameters: query (keywords, omittable to get recent items). The kind enum values (decision, convention, gotcha, fact, todo) and limit are left entirely unexplained in both schema and description, so an agent cannot tell what filtering by kind actually does.

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 ('Search this project's memories') plus the retrieval mechanism (BM25 full-text search), which is concrete enough to distinguish it from the write-oriented siblings like remember and forget. It does not, however, differentiate itself from list_memories, since 'omit query to get the most recent memories' describes behavior that sibling plausibly also offers.

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 activation context: 'Call at the start of a task.' That is actionable guidance for an agent planning a workflow. It names no alternatives or when-not conditions (e.g. when to prefer list_memories or confirm_memory instead), so it stops short of full routing guidance.

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