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

Goes well beyond annotations by disclosing return format (top-N passages with character offsets and similarity scores), technical implementation (BGE-base-en embeddings, cosine, 500-char overlapping windows), and input limits (200K chars with truncation and flagging). This rich behavioral detail helps agents anticipate edge cases and interpret results, without contradicting the readOnly/idempotent 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 front-loaded with the core action in the first sentence, then each subsequent sentence adds a distinct piece of information: use case, output details, workflow pairing, and technical limits. No filler or repetition; every sentence earns its place.

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 having no output schema, the description explains what the tool returns (passages with offsets and scores). Combined with thorough annotations (read-only, idempotent, non-destructive) and a fully documented schema, it covers the tool's complexity, limitations, and typical use context comprehensively. The description alone would be sufficient for an agent to select and invoke the tool correctly.

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% with detailed parameter descriptions, so the baseline is 3. The description adds helpful examples for the text parameter (SEC 10-K, article, long tool result) and re-emphasizes that the query is natural-language, but it does not introduce significant new semantic meaning beyond the schema. The truncation note is a behavioral trait rather than parameter semantics.

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?

Description opens with a specific verb-resource pairing: 'Semantic search INSIDE a fetched record', clearly distinguishing it from general search tools. It explicitly contrasts with ask_pipeworx_grounded by explaining that search_within operates on already-fetched text and returns passages, making the tool's role unambiguous.

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?

Provides explicit when-to-use guidance: 'Use when the record is too big to cram into the prompt — search_within saves context'. It also names a sibling tool (ask_pipeworx_grounded) and describes a complementary workflow, giving agents clear direction on how this tool fits into a larger process.

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