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

Beyond the annotations (readOnly, idempotent, openWorld, non-destructive), the description adds significant behavioral context: 'BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged)' and 'every passage carries an offset so the agent can verify a verbatim quote.' This details the embedding model, chunking strategy, truncation behavior, and output features — well beyond what annotations alone could convey.

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 structured with a clear lead sentence, usage guidance, workflow pairing, and technical details. Each sentence contributes value, but the technical details make it a bit longer than strictly necessary. It remains well-organized and front-loaded, earning a 4 rather than a 5 due to slight density.

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 tool has no output schema, so the description must explain return values — and it does: 'get back the top-N passages with character offsets and similarity scores.' It also covers input constraints (200K chars), use case (large records), and integration (ask_pipeworx_grounded). Combined with thorough annotations and schema, the description is complete for an agent to select and invoke correctly.

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%, so each parameter already has a description. However, the description enhances the meaning of 'text' by noting the 200K char cap and truncation flag, and it clarifies how 'query' is used with natural-language examples. It also explains the relationship between text and output (window size), adding context not present in the schema. This exceeds the baseline 3 for high schema coverage.

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 a specific action ('Semantic search') on a specific resource ('INSIDE a fetched record'), and immediately differentiates itself from siblings by emphasizing 'Pass the text you already pulled' — making it clear this is for searching within user-provided text, not external sources. This contrasts with sibling tools like ask_pipeworx_grounded and ask_pipeworx, which likely operate on whole documents or external data.

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 gives explicit guidance: 'Use when the record is too big to cram into the prompt' and explicitly names an alternative and pairing: 'Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document.' This tells the agent both when to use this tool and how it fits into a larger workflow, satisfying the 'when/when-not/alternatives' criterion.

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