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

Beyond the annotations (readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false), the description discloses critical behavioral traits: the tool performs routing and fetching before extraction, it returns a structured refusal object with specific refusal_reason values, it never invents facts, and it costs an extra LLM call. This adds substantial context beyond what annotations provide, especially the explicit refusal behavior which is essential for an agent to handle failure modes correctly.

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 dense but structured: it leads with the compelling differentiator (hallucination-resistant), then explains the mechanism, return shape, refusal cases, usage guidance, and cost tradeoff. It's longer than strictly necessary, but every sentence carries meaningful information. The front-loading of the key value proposition is strong. Slight deduction for the lengthy enumeration of refusal_reason values which partially duplicates the schema details.

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 the tool's complexity (routing across 5,743 tools, extraction, refusal handling), the description covers the essential context: what the tool does, how it behaves on success and failure, when to prefer it, and when to avoid it. The output schema is not provided, but the description explicitly lists the return fields and refusal reasons, so an agent understands the full contract. No critical missing information for an agent to select and invoke the tool 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?

Schema description coverage is 100%, so the baseline is 3. The description adds value by explaining that the single required parameter (question) is the natural-language query that gets routed to the right tool, and that the tool fills arguments—this contextualizes the parameter's role in the overall process. It doesn't provide per-parameter semantics beyond what the schema already covers, but it does clarify the question's purpose in the extraction pipeline.

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's purpose: a hallucination-resistant answer mode for high-stakes reads, and explicitly differentiates it from its sibling ask_pipeworx by noting it extracts answers only from tool results and returns refusals when data doesn't directly answer. The verb 'EXTRACTS' and the explicit refusal schema make the purpose unambiguous.

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 explicit guidance on when to use this tool vs alternatives: 'Use whenever an answer will be quoted, cited, or acted on...' and 'prefer ask_pipeworx for casual lookups.' It also explains the routing behavior ('Same routing as ask_pipeworx') and the cost tradeoff ('Costs one extra LLM call'), which helps an agent decide between the two siblings.

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