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

Beyond the annotations (readOnlyHint, idempotentHint, etc.), the description discloses significant behavioral traits: it strictly extracts answers from tool results only ('using ONLY what the tool result contains'), returns a specific structured response including evidence and refusal reasons, and handles refusal cases with explicit reasons (not_in_source, no_tool_match, etc.). It also mentions the extra LLM call cost. This goes well beyond the annotations and gives the agent full transparency into how the tool behaves.

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 well-structured and front-loaded: it opens with the core purpose, then explains the mechanism, return format, refusal reasons, and usage guidance, and ends with a cost comparison. Each sentence provides essential information without redundancy. Despite being longer than typical descriptions, every part earns its place; there is no fluff or repetition.

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?

For a tool with this complexity, the description covers all necessary aspects: purpose, behavior, return structure (including evidence and refusal reasons), usage guidelines, and cost trade-offs. Even without an output schema, the description explicitly details what the tool returns on success and failure. The agent is fully equipped to decide when to call this tool and what to expect from the response.

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 schema description already fully documents the 'question' parameter and its aliases (100% coverage). The description does not add additional parameter semantics beyond what the schema provides—it only mentions that it 'fills arguments' and 'fetches the data', which is generic and already implied. According to the rubric, with schema coverage >80%, a baseline of 3 is appropriate when no additional parameter insight is given. The description does not describe question format, examples, or constraints beyond natural language.

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 states a specific purpose: a hallucination-resistant answer mode for high-stakes reads, and explicitly contrasts with ask_pipeworx ('Same routing as ask_pipeworx ... then EXTRACTS'). It identifies the verb (extract), the resource (answers from tool results), and the mode (grounded). The phrase 'Use whenever an answer will be quoted, cited, or acted on' further clarifies the target use case. This clearly distinguishes it from siblings like ask_pipeworx and ask_pipeworx_beta.

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 the tool ('Use whenever an answer will be quoted, cited, or acted on...') and when not to ('prefer ask_pipeworx for casual lookups'). It names the alternative (ask_pipeworx) and the cost trade-off ('Costs one extra LLM call'). This gives the agent explicit decision criteria for selecting this tool over its siblings.

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