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

Beyond annotations (readOnly, openWorld, idempotent), the description discloses the embedding model (BGE-base-en), chunking (500-char overlapping windows), similarity measure (cosine), and truncation behavior (200K cap with flag). These details help the agent understand behavior and limitations.

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?

Three sentences: action, usage guideline, technical detail. No fluff. Front-loaded with the core action. Every sentence serves a purpose.

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 explains the return format (passages with offsets and scores) despite no output schema. It also mentions pairing with a sibling tool. However, it doesn't specify ordering of passages or score ranges, which could add more completeness.

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 value by giving concrete examples for 'text' (e.g., SEC 10-K body) and 'query' (e.g., supply-chain risk), clarifying usage. It doesn't add new parameter details but provides helpful context.

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 performs semantic search inside a fetched record, specifying the inputs (text and query) and outputs (top-N passages with offsets and scores). It distinguishes itself from siblings by explaining it saves context and pairs with ask_pipeworx_grounded.

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?

Explicitly states when to use: 'Use when the record is too big to cram into the prompt.' Provides a complementary tool (ask_pipeworx_grounded) for grounding. Also notes the 200K char limit, helping the agent decide.

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