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

Annotations already mark it read-only and idempotent, but the description goes well beyond: it discloses the embedding model (BGE-base-en), windowing (500-char overlapping), distance metric (cosine), the 200K char cap with truncation and flagging, and that passages include character offsets for quote verification. This rich behavioral detail is exactly what an agent needs to predict results.

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?

Every sentence earns its place: the first defines the action, the second covers when to use, the third pairs with a sibling, and the last provides technical constraints. Despite its density, it is tightly written with no filler, front-loading the most critical information.

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 carries the full burden of explaining return values, and it does: passages, offsets, and similarity scores. It also covers edge cases (truncation flag) and algorithm details, making the tool's behavior fully predictable for an agent that may need to act on the results.

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 parameters are documented, but the description adds meaningful context: 'text you already pulled' clarifies the resource type, 'natural-language query' and examples illustrate query usage, and 'top-N passages' reinforces the limit parameter. It also explains how parameters interact with the search mechanism, adding value beyond 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 'Semantic search INSIDE a fetched record,' using a specific verb and resource that clearly defines the tool's function. It contrasts with sibling tools by noting it returns passages with offsets rather than whole-document answers, and explicitly pairs with ask_pipeworx_grounded, 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,' and explains how it saves context. It also provides a usage workflow with ask_pipeworx_grounded, effectively steering the agent to the right alternative for grounding over relevant passages.

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