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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses the full behavioral contract: the exact success return shape with evidence and confidence fields, the explicit refusal path with a fixed set of refusal_reason values, and the grounded constraint that the answer is derived only from the tool result. It also surfaces the extra LLM call cost. This adds substantial beyond-annotation value with no contradictions.

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 densely informative and front-loaded with the key differentiator ('Hallucination-resistant'). Each section — purpose, routing mechanics, return contract, usage guidance, cost trade-off — earns its place. It is longer than minimal but the length is justified by the tool's complex refusal behavior and the critical citation use-case. A slight trim of the full refusal_reason enum could make it tighter, hence 4 rather than 5.

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 no output schema, the description fully explains both success and refusal outputs, the grounded behavior, when to use it, and when not to. It handles the complexity of a tool that routes across 5,798 tools by describing the orchestration at the right granularity. The parameter side is also adequately covered by the schema. Nothing critical is missing for an agent to call this 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?

The only real parameter 'question' is fully documented in the schema with a clear description and alias list, achieving 100% schema description coverage. The tool description does not add param-specific semantics beyond explaining the general question-answering flow, but with the schema already carrying the burden, the baseline 3 is appropriate. No additional parameter detail is strictly needed.

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 purpose — 'Hallucination-resistant answer mode for high-stakes reads' — then elaborates with a clear process: tool selection, argument filling, data fetching, and answer extraction restricted to tool results. It directly distinguishes itself from ask_pipeworx by naming the sibling and describing the difference in behavior. An agent can confidently tell what this tool does and when it is the right choice.

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 gives explicit when-to-use guidance: whenever the answer will be quoted, cited, or acted on and the agent must not invent facts, with concrete examples (financial verdicts, legal claims, medical lookups, public statements). It also provides a clear trade-off and exclusion: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' This is exceptional routing guidance.

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