List AI Coach memos

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description's closing "Read-only" is consistent, not contradictory. The description adds substantial behavioral value beyond annotations: newest-first ordering, the exact field set returned, the explicit exclusion of the full body, and one-level group organization semantics. Rich, useful disclosure of mutation-free behavior.

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?

Four sentences, front-loaded with the core purpose and ordering, then the return-shape caveat, then group semantics and routing. Efficient and no fluff, though the final "Read-only" duplicates what the annotation already states — a minor redundancy, not waste.

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?

Complete for a metadata-list tool: it has an output schema, 100% parameter coverage, and the description explains ordering, returned fields, group filtering semantics, and routes to the read sibling for bodies. Nothing an agent needs to invoke it correctly is missing.

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% — all four parameters (group, limit, locale, offset) are documented in the schema. The description reinforces the group semantics (one-level, empty string = ungrouped) but does not add meaning beyond the schema's own parameter descriptions. Baseline 3 is appropriate when the schema carries the load.

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 — "List the user's memos in AI Coach, newest first" — and immediately differentiates it from the read sibling by declaring it returns metadata (noteId, title, last modified, size, group, excerpt) and not the full body, then points to read_ai_coach_note for the body. An agent can distinguish list vs read vs search on sight.

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 routing guidance: "Use read_ai_coach_note to get the body" names the alternative and the condition that selects it. Group-filtering semantics are explained (one group vs empty string vs omit). However, it does not explicitly address when to prefer this over search_ai_coach_notes, so the exclusion guidance is slightly incomplete.

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