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

Beyond the read-only and idempotent annotations, the description discloses specific internal mechanics: 'BGE-base-en embeddings + cosine over 500-char overlapping windows' and the hard cap of 200K chars with truncation flagging. It also explains that passages carry character offsets for verbatim verification, which adds meaningful behavioral context beyond what annotations alone provide.

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 a single, information-dense paragraph that front-loads the core purpose. It covers purpose, usage, output, pairing, and technical constraints in about five sentences. Each sentence earns its place, though it is slightly longer than the two-sentence gold standard. Structure could be improved with line breaks, but the content remains well-organized.

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?

Since there is no output schema, the description carries the full burden of explaining what the tool returns, and it does so clearly: top-N passages, offsets, similarity scores, and truncation flag. It also covers limits, algorithm, pairing, and use cases. This is a complete description 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 coverage is 100%, with each parameter already described (text, limit with range/default, query with examples). The description adds minimal new parameter-specific meaning, such as clarifying that text is 'already pulled' and giving examples of document types, but these are not substantial beyond the schema. Baseline 3 is appropriate.

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+resource: 'Semantic search INSIDE a fetched record' and clearly states the output (top-N passages with character offsets and similarity scores). It differentiates from siblings by explicitly scoping to pre-fetched text and pairing with ask_pipeworx_grounded, making the tool's niche 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?

The description provides a clear when-to-use condition: 'Use when the record is too big to cram into the prompt' and explains the benefit (saves context, returns only relevant passages). It also gives a complementary workflow with ask_pipeworx_grounded, serving as an alternative/companion usage pattern. This is explicit and actionable.

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