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

Although annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, the description adds valuable behavioral context beyond those flags: truncation behavior ('cap is 200K chars (longer inputs are truncated and flagged)'), implementation details ('BGE-base-en embeddings + cosine over 500-char overlapping windows'), and output feature ('every passage carries an offset so the agent can verify a verbatim quote'). No contradiction with annotations is present.

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 tightly written and front-loaded: the first sentence gives the core purpose, followed by mechanics, usage condition, integration, and implementation details. Each sentence earns its place—there is no filler or repetition. The only possible redundancy is the cap mention in both the schema and description, but it is justified as a behavioral clue for the agent.

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?

There is no output schema, so the description needs to explain return values; it does so by stating 'top-N passages with character offsets and similarity scores.' It also covers input limits, truncation flag, and integration workflow. A fully explicit response structure (e.g., exact JSON format of each passage) is not specified, but the description provides enough for an agent to understand what will be returned and how to use it.

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 description coverage is 100%, so the baseline is 3. The tool description reinforces the role of each parameter ('text you already pulled', 'natural-language query', 'top-N passages') but does not add new details beyond the schema. The schema already documents text length, query examples, and limit range/default, so the description adds minimal parameter-specific value.

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 and resource: 'Semantic search INSIDE a fetched record.' It clearly distinguishes from siblings by explaining it operates on already-fetched text and returns passages with offsets and similarity scores, and explicitly pairs with ask_pipeworx_grounded, which uses the gateway to fetch. This makes differentiation from other search or Q&A tools immediate.

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 states an explicit condition: 'Use when the record is too big to cram into the prompt.' It also provides a concrete workflow: 'fetch with the gateway, ground over the relevant passages instead of the whole document,' which routes the agent to the correct alternative (ask_pipeworx_grounded) and clarifies this tool is for offline passage extraction. This is strong guidance with clear exclusions and integration hints.

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