search

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 adds one genuinely useful behavioral trait: the model warm-up performance note ('the first call after the server starts is slower, every later one is instant'). This helps an agent set expectations for latency. However, it does not disclose the return format, error behavior, or result limits beyond the k parameter. Partial but non-trivial disclosure.

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?

The description is compact at roughly 40 words and front-loads the core purpose. However, the flow is disjointed — it jumps from purpose to an implementation pipeline ('mmlw -> reranker') to a parameter explanation to a performance note. The '(mmlw -> reranker)' fragment is cryptic jargon that earns little value for an agent, and the mixing of parameter docs and behavioral notes in one block hurts scanability.

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 tool with 4 parameters, 0% schema coverage, and no output schema, the description is incomplete. It clarifies client but leaves query semantics, k's effect on result count, rerank's behavior, and the response shape unaddressed. An agent cannot fully predict how results will be structured or how filtering interacts with the client parameter. Significant gaps remain for a moderately complex search 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 0%, so the description must compensate. It adds real meaning to the client parameter ('owner slug, or empty for everyone plus global'), which is not derivable from the schema alone. But k, query, and rerank are left entirely to the schema, which at 0% coverage provides no descriptions. The description partially compensates but leaves three of four parameters undocumented.

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: 'Semantic search over facts/documents'. This clearly differentiates from siblings like list_facts, get_fact, and check — search is a similarity lookup rather than retrieval of a specific item. However, it doesn't explicitly name any sibling or say what it is not, and the '(mmlw -> reranker)' implementation detail adds noise without clarifying purpose.

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 phrase 'Semantic search over facts/documents' implies the tool is for similarity-based retrieval, which suggests when an agent would prefer it over list_facts or get_fact. But there is no explicit when-to-use versus when-not-to-use guidance, no alternatives named, and no exclusion conditions stated. The usage context is implied rather than stated.

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