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

The description discloses key behaviors beyond annotations: truncation at 200K chars (with a flag), overlapping 500-char windows, BGE-base-en embeddings with cosine similarity, and that every passage includes an offset for verifiability. This adds significant context to the readOnly/idempotent hints.

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 detailed but every sentence adds value: purpose, use case, truncation behavior, algorithm, and pairing with a sibling tool. It is front-loaded with the core action and efficiently structured with semicolons and examples, earning its length.

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?

Given there is no output schema, the description adequately covers return values (passages with character offsets and similarity scores). It also explains the technical specifics (window size, embedding model, truncation) and provides a clear use case, making the tool fully understandable for an AI agent without further information.

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% for all three parameters, so the baseline is 3. The description adds minor context (e.g., 'text you already pulled' as a usage nuance, 'top-N passages' reinforcing the limit parameter), but does not materially extend the parameter meanings provided by the 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 clearly states the tool's function: semantic search inside a previously fetched text, returning top-N passages with offsets and scores. It distinguishes itself from siblings like search_wikipedia (external search) and ask_pipeworx_grounded (grounded QA) by emphasizing it operates on a passed-in text.

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?

Explicit usage guidance is provided: 'Use when the record is too big to cram into the prompt.' It also names a complementary tool ('Pairs with ask_pipeworx_grounded') and explains the workflow: fetch with the gateway, then ground over passages. This directly informs when to choose this tool over alternatives.

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