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

The description reveals substantial behavioral detail beyond annotations: it returns top-N passages with character offsets and similarity scores, uses BGE-base-en embeddings and cosine similarity over 500-char overlapping windows, and has a 200K character cap with truncation flagged. This gives the agent a clear model of what to expect. No contradiction with the readOnly/idempotent 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 three sentences, each earning its place. The first sentence states the core function, the second gives the primary use case and return characteristics, and the third covers technical details and limits. There is no redundancy or fluff; the front-loaded phrase 'Semantic search INSIDE a fetched record' immediately conveys the purpose.

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?

The description covers the key aspects an agent needs: what it does, when to use it, what it returns (offsets, scores), how it works (embeddings, window size), and its limits (200K truncation). Since there is no output schema, the description compensates by summarizing the return structure. The guidance on pairing with ask_pipeworx_grounded also rounds out the usage context. This is complete for a tool of this complexity.

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?

The input schema already provides 100% coverage with descriptions for all three parameters, so the baseline is 3. The description adds value by providing concrete examples of valid inputs (SEC 10-K body, article, natural-language query examples) and framing the text parameter as a 'fetched record,' which enriches the schema's bare description. This extra context justifies a score above baseline.

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 opens with 'Semantic search INSIDE a fetched record,' clearly specifying the verb (search) and the resource (a fetched record). It distinguishes itself from siblings like search_markets and ask_pipeworx by emphasizing that it operates on text already pulled by the agent, not on external market data or general queries.

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 description explicitly states when to use the tool: 'Use when the record is too big to cram into the prompt.' It also provides a concrete integration pattern with ask_pipeworx_grounded, showing how to fetch then ground over passages, which clarifies the intended workflow relative to siblings.

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