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

Annotations already mark readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description goes well beyond those by disclosing truncation at 200K chars with a flag, the BGE-base-en embedding model, cosine similarity over 500-char overlapping windows, and the return of offsets and similarity scores—all behavior not present in the 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?

Three dense sentences front-load the core operation and value, then cover use case, pairing, mechanism, and limits. Every clause contributes information; there is no filler or repetition of the title.

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?

With no output schema, the description still fully conveys the return shape (top-N passages with character offsets and similarity scores), the operational constraints (200K cap, truncation flag), the intended use case, and how the tool fits with a sibling tool. This is complete for an agent to select and invoke it 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%, so the schema already documents text, query, and limit with defaults and examples. The description adds meaning by framing text as 'the text you already pulled' and by noting the truncation/flag behavior for oversized inputs, which is a useful behavioral nuance not in 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 differentiates from sibling tools by emphasizing that it operates on text already pulled (e.g., a SEC 10-K, an article) rather than performing a global search, and explicitly names ask_pipeworx_grounded as a related but distinct workflow.

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?

It gives direct guidance: 'Use when the record is too big to cram into the prompt.' It also contrasts with ask_pipeworx_grounded by recommending a fetch-with-gateway then ground-over-relevant-passages pattern, and explains the benefit (saves context, verifiable offsets). This is explicit when-to-use and alternative-naming.

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