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

The description discloses implementation details beyond the read-only annotation: BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, a 200K character cap with truncation flagging, and the presence of offsets for verification. These details help the agent predict performance and failure modes, adding significant value over the annotation's mere read-only hint.

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 front-loaded with the core purpose and is dense with useful information: use case, pairing, mechanism, and limits. Every sentence earns its place, though the density and length make it slightly less concise than the two-sentence gold standard. It remains highly readable and well-structured.

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 no output schema, the description fully discloses the return format (top-N passages with character offsets and similarity scores) and the edge case of input truncation with a flag. It also explains how it integrates with the broader tool ecosystem (fetch with gateway, ground with ask_pipeworx_grounded). This is complete for effective selection and invocation.

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 schema already covers all three parameters with examples, so the baseline is 3. The description adds contextual meaning by explaining the 'text' parameter as a previously fetched record (e.g., SEC 10-K, article) and clarifies the 'query' with concrete examples. It also mentions the truncation flag, which elaborates on the 'text' cap. Thus it exceeds the baseline slightly.

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 a specific verb+resource: "Semantic search INSIDE a fetched record." It clearly distinguishes from siblings by explaining the use case (searching inside an already-fetched record) and explicitly pairs with ask_pipeworx_grounded as the complementary tool. This prevents confusion with other query-based tools.

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 states when to use the tool: "when the record is too big to cram into the prompt." It also names the alternative workflow with ask_pipeworx_grounded, explaining the distinction between fetching and grounding. This gives the agent explicit decision criteria and compares against a sibling tool.

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