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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the description only needs to add context, and it does: it discloses the exact response envelope and the id-prefix convention (task:12, note:5). There is no output schema, so this return-shape disclosure is real added value; only result limits or pagination behavior are unstated.

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?

Two short sentences with zero filler, front-loading what is searched before the return format and the follow-up action. The inline JSON shape is compact and unambiguous rather than verbose.

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 one-parameter search tool with no output schema, the description covers the return shape and the next step an agent must take, which is the essential context. It falls short only on how many results come back, whether paging exists, and which record types are covered.

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?

There is a single parameter with 100% schema description coverage, including the minimum length constraint, so the schema already carries the semantics. The description adds nothing about query syntax, matching behavior, or scope of entity types searched, so the baseline of 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: "Recherche dans les données Dandori de l'utilisateur", which tells an agent exactly what corpus is being searched. It also implicitly separates itself from the sibling fetch by explaining that fetch reads a single id in full, though it does not distinguish itself from the sibling dandori_search.

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?

The description gives a follow-up workflow rule — take an id from results and read it in full with fetch — which is genuine usage context. However, it never states when to use this tool versus the similarly named dandori_search sibling, nor any preconditions or exclusions, leaving the selection decision implied.

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