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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description adds valuable behavioral details: returns character offsets and similarity scores, uses BGE-base-en embeddings with cosine similarity over 500-char overlapping windows, and enforces a 200K char cap with truncation and flagging. This goes well beyond the structured fields, explaining internal mechanics and edge-case behavior.

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 structured: the first sentence states the core function, the second gives usage context, the third provides an integration pattern, and the fourth covers technical details. Every sentence adds essential information without redundancy, wordiness, or trivial repetition of the tool name.

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 lacking an output schema, the description tells the agent exactly what to expect: 'top-N passages with character offsets and similarity scores.' It also covers input constraints (200K chars), windowing behavior, and truncation flagging. The pairing with ask_pipeworx_grounded provides a complete workflow, making the tool understandable in context without needing additional documentation.

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 parameters are fully documented. The description adds contextual meaning by giving concrete examples for 'text' (e.g., 'SEC 10-K body, an article, a long tool result') and for 'query' (e.g., 'supply-chain risk', 'fiscal year 2024 revenue'). It also implies 'limit' semantics by saying 'top-N passages' and 'returns only the passages that matter,' though the limit parameter itself is left to 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 opens with a specific verb and resource: 'Semantic search INSIDE a fetched record.' It clearly distinguishes itself from siblings by emphasizing it works on already-fetched text, not external sources, and explicitly differentiates the return type (top-N passages with offsets and similarity scores). It also references a companion tool (ask_pipeworx_grounded), further disambiguating its role.

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 gives explicit guidance: 'Use when the record is too big to cram into the prompt' and explains the benefit of saving context. It also provides an alternative/companion pattern: 'Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document.' This tells the agent when and how to use it versus alternatives.

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