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

Despite annotations already declaring readOnlyHint=true and destructiveHint=false, the description adds valuable behavioral details: the use of BGE-base-en embeddings with cosine similarity, overlapping 500-char windows, a 200K character limit with truncation flagging, and the fact that passages include character offsets for verbatim verification. These go beyond the annotations and give the agent confidence in the tool's internals and edge cases.

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 long and front-loads the core purpose. The first sentence states what it does, the second gives the use case and benefits, the third provides technical details and limits. Every sentence adds necessary information without fluff, making it dense yet clear.

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 is complete for a search tool: it explains what outputs to expect (top-N passages with character offsets and similarity scores), mentions the truncation flag, and ties the tool to a sibling workflow. Given no output schema exists, the description compensates by describing the return format and the embedding/windowing behavior, so the agent has enough context to invoke and use the tool 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?

The schema covers 100% of parameters, so the baseline is 3. The description adds extra meaning by explaining the 'text' parameter as 'the text you already pulled' with concrete examples (SEC 10-K body, article), and gives illustrative queries for 'query' (e.g., 'supply-chain risk'). This enriches the schema definitions, though the 'limit' parameter is not elaborated further.

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,' which clearly states the action (semantic search), the resource (a fetched record), and distinguishes it from siblings like ask_pipeworx_grounded (which grounds over the whole document) and get_granule/get_package (which fetch). The verb 'search' is specific and the scope 'inside a fetched record' is unambiguous.

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 this tool: 'Use when the record is too big to cram into the prompt.' It also provides a direct pairing with ask_pipeworx_grounded, explaining the workflow: fetch with the gateway, then ground over relevant passages. This gives clear guidance on the tool's role relative to alternatives.

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