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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses the extraction-only behavior, the exact success and refusal return shapes, the list of refusal_reason values, and the additional cost. This fully characterizes the tool's behavior without contradicting annotations.

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 longer than average but every sentence adds value: purpose, mechanism, return contracts, use cases, and cost tradeoff. Slightly dense formatting, but well front-loaded with the core purpose before implementation 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 no output schema, the description fully covers the return format, all refusal modes, the routing scale, the single required natural-language parameter, and the relationship to its sibling tool. Nothing needed for correct invocation or interpretation is missing.

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 input schema is fully self-documenting (100% coverage) with all aliases explained, so the description does not need to add parameter detail. It only implies that 'question' is routed through tool selection, which is already obvious from the tool name and schema.

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 defines a specific mode: 'hallucination-resistant answer mode for high-stakes reads' that extracts answers only from fetched tool results. It distinguishes itself from the sibling ask_pipeworx by describing identical routing but a stricter extraction behavior, so an agent can tell them apart.

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?

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 domains. It also gives a when-not-to-use: 'prefer ask_pipeworx for casual lookups' and mentions the one-extra-LLM-call tradeoff.

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