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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description goes well beyond that: it discloses the refusal mechanism with the full enumerated refusal_reason set (not_in_source, no_tool_match, tool_error, data_truncated, llm_error), the exact success return shape with evidence as a verbatim quote, and the cost tradeoff of one extra LLM call. This is precisely the behavioral nuance an agent needs to distinguish a legitimate refusal from a failure.

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 long but every sentence earns its place: purpose, mechanics, success/failure return shapes, usage guidance, and cost tradeoff. With no output schema present, spelling out the return contract in the description is justified rather than redundant. It is slightly dense, but the key differentiator ('hallucination-resistant') is front-loaded and the content is nearly all high-signal.

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 one real parameter and no output schema, this description is complete: it covers the return format for both success and refusal paths, enumerates every refusal reason, explains the cost differential versus the sibling, and states the scope of what the tool will and will not do (will not invent facts; will refuse instead). An agent has everything needed to invoke it correctly and interpret its result.

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% — all 6 parameters are documented alias names for the single 'question' string, so the schema fully carries parameter semantics. The description adds context about what happens to the question (routing across 5,798 tools, argument filling) but no syntax or format detail beyond the schema. Baseline 3 is appropriate since the 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 opens with a specific mode definition ('Hallucination-resistant answer mode for high-stakes reads') and names the exact verb+resource behavior: route, fetch, then extract an answer using only tool results. It explicitly differentiates from the sibling ask_pipeworx ('Same routing as ask_pipeworx... then EXTRACTS the answer using ONLY what the tool result contains'), so an agent can distinguish them without opening either schema.

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?

Gives explicit when-to-use guidance ('Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts') with concrete high-stakes domains listed (financial verdicts, legal claims, medical lookups, public statements). Also gives an explicit when-not-to-use and the preferred alternative: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' Nothing is left to inference.

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