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

While annotations already declare readOnlyHint and idempotentHint, the description adds substantial behavioral context: mentions BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, the 200K character cap, and that longer inputs are truncated and flagged. It also discloses that results include character offsets and similarity scores, which goes well beyond the 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 compact but dense: the opening sentence states the core action, the middle explains usage, and the final sentence covers technical limitations. Every sentence provides unique value, with no filler or tautology. It is appropriately front-loaded with the most important purpose information.

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?

Despite no output schema, the description tells the agent exactly what to expect: 'top-N passages with character offsets and similarity scores.' It covers input constraints (character cap), algorithmic nuances (overlapping windows), and integration with sibling tools. The tool's complexity is fully addressed, making it nearly self-contained for an agent.

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 baseline is 3. The description adds practical semantics by framing 'text' as content already pulled (e.g., SEC 10-K body) and clarifying that 'limit' yields 'top-N passages.' It reinforces the natural-language nature of 'query' with concrete examples, and explains that the text parameter is subject to a 200K truncation cap, adding meaning beyond the raw schema.

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,' a specific verb+resource pairing that clearly distinguishes this from sibling tools like ask_pipeworx. It further differentiates by emphasizing that it operates on text already retrieved, in contrast to question-answering tools, and describes the exact output (passages with offsets and scores).

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 alternative/complement: 'Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document,' giving clear guidance on how it fits into a workflow.

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