search_keywords

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

Annotations already declare readOnlyHint=true, so safety is covered; the description adds genuinely new behavioral facts: results are ranked with scores, archived thoughts are excluded, and there is no parameter to widen scope. That last constraint is exactly the kind of non-obvious behavior an agent needs. It stops short of describing pagination or scoring normalization.

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 short sentences, each load-bearing: purpose, return shape, and the exclusion constraint. No filler, and the core capability is front-loaded.

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?

Output schema exists and the description still helpfully summarizes the return shape, and read-only safety is annotated. The significant remaining gap is parameter semantics: with a 0% schema coverage on two parameters, an agent lacks guidance on query syntax and result-set sizing.

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% for two parameters, so the description must carry the burden, and it does not: neither 'query' (syntax, whether BM25 operators are supported) nor 'top_k' (default 10, max 1000) is addressed. The only parameter-adjacent statement is the negative one about no filter existing, which is marginal.

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 ('Full-text BM25 keyword search over stored memory') plus the return shape ('ranked thought identifiers with scores'), which is more than the bare name conveys. It does not, however, distinguish itself from siblings like search_memory or query_memory, so an agent must infer the keyword-vs-semantic split.

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 'BM25 keyword' framing implies exact-term lookup rather than semantic retrieval, which hints at when to pick this over search_memory/query_memory. But no alternative is named and no explicit when/when-not condition is stated, so the routing guidance is only implied.

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