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

Annotations declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds meaningful context beyond these: it reveals the embedding model (BGE-base-en), the similarity method (cosine), the windowing strategy (500-char overlapping), the 200K character cap, and the truncation flag behavior. It also discloses the return shape (passages with offsets and scores). No contradictions 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 multi-sentence but every sentence adds a distinct piece of information: the core action, the use case, the return format, the algorithmic details, and the pairing with a sibling tool. It is front-loaded with the action and use case, then moves to technical specifics. No filler or repetition.

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 moderately complex tool with 3 parameters and no output schema, the description covers all essential aspects: purpose, when to use, what to pass, what to expect in return (offsets and scores), constraints (200K cap, truncation flag), and relationship to a sibling tool. The absence of an output schema is compensated by explicitly describing return values.

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 the baseline is 3. The description adds value on top: it clarifies what 'text' should contain (already-fetched record content), gives example queries, and implies the meaning of 'limit' as 'top-N passages'. This enhances the schema's bare descriptions without being redundant.

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 it performs semantic search inside a fetched record ('Search INSIDE a fetched record'), with specific examples (SEC 10-K body, article) and a contrast against alternatives. It distinguishes itself from sibling 'ask_pipeworx_grounded' by positioning it as the inside-search complement to a fetch-then-ground workflow.

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?

Explicitly states when to use: 'Use when the record is too big to cram into the prompt'. It also names an alternative, 'ask_pipeworx_grounded', and explains how to pair with it ('fetch with the gateway, ground over the relevant passages'). No ambiguity about when this tool is the right choice.

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