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

Beyond the read-only/idempotent annotations, it discloses that ranking covers only a partial embedded subset, that similarity is not treatment or validity, that matched_text is null about 10% of the time with a status reason, and that an embedding outage yields a 503 rather than an empty match. That is exactly the kind of failure-mode context annotations cannot carry.

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?

It front-loads purpose, then results, then limits, which is a sensible order, and nearly every sentence carries a distinct constraint. It is dense and runs long, with the coverage/degraded-state material packed into a single block that would read better as separate clauses, costing a point.

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, so describing the returned fields (opinion_id, distance, similarity, matched_text_status, same_case_other_opinions, duplicate_records) is necessary and is done. Combined with coverage, cutoff date, and degraded-state behavior, an agent has everything needed to call it and interpret the response correctly.

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 100% and both parameters (q with 3-200 length, limit 1-20) are already documented in the schema, so the description adds little parameter guidance. Its value instead goes to return-field semantics, which is a different dimension. 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?

The description states a specific verb and resource ('semantic (vector) search over embedded opinion chunks') plus its scope and matching mode, and explicitly distinguishes itself from the sibling 'fts' route. An agent can tell it apart from search, fts, or similar without opening a schema.

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?

It states the selecting condition ('when there is no fixed term of art') and names the alternative route ('fts is a separate route'), so the choice between keyword and concept search is explicit rather than inferred. It also warns against misreading a thin result for recent authority, which governs how to interpret use near the collection edge.

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