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

Annotations already declare read-only, idempotent, closed-world behavior, so the safety profile is covered. The description adds real context beyond that: local embedding lookup with no API key, scores as ranking hints rather than proof, and the scope limitation that bulk candidate generation must be done offline.

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 short, front-loaded sentences with no filler; the core operation leads and the cautions follow. The telegraphic phrasing ('no threshold proves a reprint') is dense but each sentence carries distinct information.

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?

An output schema exists, so return values need not be enumerated, and annotations cover the safety profile. The description supplies the interpretive cautions and scope limits an agent needs to use the scores correctly, leaving little missing for a four-parameter lookup tool.

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%, so id, limit, subset and min_score are fully documented in the schema. The description adds no syntax, default, or interpretation detail for any parameter, which is the expected baseline when the schema does the work.

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 operation on a specific resource: nearest stored embeddings ranked by cosine similarity, computed locally 'without an API key'. That clearly separates it from the search_* family, though no sibling is named explicitly.

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 both a use case ('scores rank reading candidates') and a negative boundary ('corpus-wide candidate generation belongs offline'), plus a caution that 'no threshold proves a reprint'. It stops short of naming which alternative tool to use for corpus-wide work.

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