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

Annotations already declare readOnly and idempotent, but the description goes far beyond: it discloses the embedding model (BGE-base-en), similarity metric (cosine), window size (500-char overlapping), response contents (passages with offsets and scores), and the 200K char truncation behavior. This is rich, non-contradictory behavioral context.

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 longer than average (four sentences), but every sentence earns its place: purpose, use case, pairing, and technical mechanics. It is front-loaded with the core action and progressively adds implementation detail, though a minor redundancy ('passages that matter' and 'top-N passages') could be trimmed.

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 explains exactly what the agent gets back (top-N passages with character offsets and similarity scores), plus the truncation flag. It covers input size limits, pairing with grounded workflows, and the technical search mechanism, making it fully self-sufficient for a tool of this complexity.

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 covers all parameters at 100%, so baseline is 3. The description adds meaningful context beyond the schema: it defines 'text' as 'the text you already pulled' with concrete examples (SEC 10-K, article, long tool result), clarifies query as a natural-language request with examples, and explains limit via 'top-N passages'. This elevates parameter understanding.

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', clearly specifying the verb (semantic search), resource (fetched record), and scope (inside it). It distinguishes itself from siblings by contrasting with ask_pipeworx_grounded and explaining the workflow pairing, making its unique role unmistakable.

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'. Names the alternative/companion ask_pipeworx_grounded with a clear workflow, but does not explicitly state when not to use it (e.g., for small records), so it falls just short of full 5.

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