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

Beyond the annotations (read-only, idempotent, open-world), the description adds substantial behavioral detail: the embedding model (BGE-base-en), similarity metric (cosine), chunking method (500-char overlapping windows), and hard input cap of 200K chars with truncation flagging. It also promises character offsets for verifiable quoting, giving the agent full transparency about how the tool operates.

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 a crisp purpose statement, followed by a use case, a pairing note, and technical constraints. Every sentence adds distinct value (purpose, when-to-use, verification benefit, implementation details), and no sentence is wasted. The density is justified by the tool's complexity.

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 fully specifies the return format (top-N passages, character offsets, similarity scores) and covers edge cases (200K char cap, truncation flag). It also situates the tool within a workflow (pairs with ask_pipeworx_grounded), making the description complete for operational decision-making.

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?

The input schema already covers 100% of parameters with clear descriptions: text (document text, max ~200K chars), query (natural-language query with examples), and limit (max passages, default 5). The description adds only minor enrichment (e.g., examples of text types like SEC 10-K), so the schema carries the interpretive burden—hence the baseline 3.

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 the specific action and resource: 'Semantic search INSIDE a fetched record.' It goes on to detail the input (text + query) and output (top-N passages with character offsets and similarity scores), and provides concrete examples (SEC 10-K, article) that make the purpose unmistakable and distinct from sibling search/Q&A tools.

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 states when to use it: 'Use when the record is too big to cram into the prompt' and explains the complementary workflow with ask_pipeworx_grounded. It does not explicitly state when not to use it (e.g., for small documents), but the guidance is clear enough for a capable agent.

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