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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses the retrieval mechanism (dense vector similarity), the embedding models used, and a deliberate behavioral choice — skipping BM25 fusion to avoid term-matching noise. This is substantive behavioral context beyond a generic 'semantic search' label, though it does not cover ranking behavior or empty-result semantics (the specter2 invisibility caveat lives only in the vectorModel parameter schema).

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 sentences with no waste: the core purpose is front-loaded, the mechanism follows, and the final sentence routes to alternatives. Every sentence earns its place, and there is no repetition of schema content or 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?

For a 14-parameter tool with an exceptionally rich schema (every parameter documented, enums explained, the SPECTER2 coverage caveat detailed), the description fully covers the selection and routing job: what the tool is, how it works, when to prefer it, and which sibling to use instead. Return-value behavior is already documented via the 'detail' parameter, so the absent output schema is not a real gap.

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 the baseline is 3. The description adds mild semantic framing for the query parameter (paraphrased ideas, 'papers arguing X') that mirrors — but does not exceed — the schema's own query description. All 14 parameters, including enums, defaults, and bounds, are already fully documented in the input schema.

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 precise verb+resource+mechanism: pure semantic (vector) search over the corpus using dense embeddings via Gemini or SPECTER2. It also names the siblings it is not ('search_keyword' for exact terms, 'search' for mixed), so an agent can differentiate it from both sibling search tools 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?

Provides explicit when-to-use guidance ('best for paraphrased queries, concept exploration, papers arguing X') and explicit when-not-to with named alternatives: 'For exact terms use search_keyword. For mixed queries use search.' It additionally explains the reasoning (skips BM25 fusion to avoid term-matching noise), letting the agent reason about the tradeoff rather than just memorize a rule.

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