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

The description adds rich behavioral details beyond annotations: it reveals the embedding model (BGE-base-en), similarity metric (cosine), chunking strategy (500-char overlapping windows), character cap (200K with truncation flag), and the inclusion of character offsets for verification. No contradiction with annotations.

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 a single dense paragraph that front-loads the core purpose and packs multiple informative details. While efficient, it could benefit from bullet points or clearer structural separation for easier scanning.

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?

No output schema exists, but the description fully explains return values: top-N passages with character offsets and similarity scores. It also covers technical details (embeddings, windowing, truncation), making the tool’s behavior and output completely understandable.

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% (all three parameters have descriptions). The description adds helpful examples for the query parameter and reiterates limits, but does not provide substantial new meaning beyond the schema. Baseline score 3 is appropriate.

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 clearly states 'Semantic search INSIDE a fetched record' and provides concrete examples (SEC 10-K, article, long tool result). It distinguishes the tool by specifying it searches within already-fetched text, contrasting with siblings like ask_pipeworx_grounded that ground over passages.

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 explicitly advises use when 'the record is too big to cram into the prompt' and explains the benefit of saving context. It also mentions pairing with ask_pipeworx_grounded, providing a clear use case. However, it does not explicitly state when not to use it or list alternative tools beyond that one pairing.

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