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

Beyond annotations (readOnly, idempotent, openWorld), the description reveals the embedding model (BGE-base-en), chunking strategy (500-char overlapping windows), character cap (200K chars with truncation flag), and output properties (offsets, similarity scores). No contradiction with 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 a single paragraph that is dense with information but not verbose. Every sentence adds value: function, use case, pairing, technical details, and limitations. No wasted words.

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?

Given no output schema, the description adequately covers return values (passages, offsets, similarity scores), technical behavior (chunking, embeddings), and limitations. It also references a sibling tool for grounding. Complete for an agent to use 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?

Input schema has 100% coverage with descriptions for text, query, and limit. The description adds value by clarifying the text size limit, providing query examples, and specifying limit range and default.

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, returning passages with offsets and scores. It distinguishes itself from siblings by specifying the context ('inside a fetched record') and provides concrete examples (SEC 10-K body, article).

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 explicitly advises using this tool when a record is too large for the prompt, and it pairs with ask_pipeworx_grounded. While it doesn't explicitly list alternatives or when not to use, the guidance is clear and actionable.

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