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

The annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true. The description adds substantial behavioral context: it describes the return format ({answer, evidence, confidence, source, fetched_at, refusal_reason}), the explicit refusal mechanism with specific refusal_reason values, and the extra LLM call cost. This goes beyond annotations but doesn't fully describe potential side effects (like whether it stores cache) or rate limits. Given the rich annotations and the extra behavioral details, 4 is appropriate.

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 front-loads the key differentiator ('Hallucination-resistant answer mode') and the return/refusal formats. Every sentence adds value: the routing explanation, the use cases, and the cost tradeoff. It's slightly long but efficient for the amount of behavior it discloses. A 4 because it could be trimmed slightly (the examples in parentheses are useful but could be shortened) but it's well-structured.

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?

Considering the complexity (it's a high-stakes reasoning tool with refusal logic), the description covers the critical aspects: when to use it, what it returns, how it handles failure, and how it differs from its sibling. It doesn't have an output schema, but the description explicitly lists the return fields and refusal reasons. It doesn't explain the routing mechanism in detail, but that's not necessary for invocation. Given the annotations and the description, it's quite complete, though it could mention error handling beyond refusal reasons.

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% for all 6 parameters, and the schema already documents the primary 'question' parameter and its aliases. The description adds minimal extra semantic meaning beyond what the schema provides – it mentions that the question should be 'in natural language' but that's also in the schema. The only extra is the clarification that all aliases map to the same question, which the schema also states. Baseline 3 is correct since schema does the heavy lifting.

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 a specific verb ('answer'), resource ('grounded mode of ask_pipeworx'), and the key differentiator: 'Hallucination-resistant answer mode for high-stakes reads.' It distinguishes itself from its sibling ask_pipeworx by explaining it extracts the answer using ONLY what the tool result contains and returns evidence. This is a strong, specific purpose statement.

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 this tool: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements).' It also names its alternative: 'prefer ask_pipeworx for casual lookups' and mentions the cost difference. This is clear, actionable guidance.

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