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

While annotations already mark the tool read-only, idempotent, and open-world, the description adds substantial behavioral detail: it routes through 5,743 tools, fills arguments, fetches data, extracts only from tool results, returns evidence/confidence/source, and yields an explicit refusal with enumerated refusal_reason values. This goes well beyond what annotations provide and prepares the agent for non-success outcomes.

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?

Every sentence earns its place. The description front-loads the essential purpose, then covers behavior, return contract, refusal modes, use cases, and cost tradeoff without repetition or filler. The return-structure details are dense but directly actionable for an agent deciding whether this tool satisfies a grounded-answer need.

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 complex tool with no output schema, the description fully covers the calling contract: what question to supply, what the success response looks like, all refusal reasons, and the precise scenario where this tool beats its cheaper sibling. The annotation-provided safety profile (read-only, idempotent) complements the description, leaving no critical gap for an agent to call it 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 coverage is 100%, with all parameters documented as aliases for 'question,' so the baseline is 3. The description reinforces that the question is high-level intent ('fills arguments' after routing) but does not add new parameter-level semantic detail beyond the schema. No penalty or bonus 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 capability: 'Hallucination-resistant answer mode for high-stakes reads.' It names the exact behavior (extracting answers using only tool results) and differentiates from the sibling ask_pipeworx by grounding and refusal semantics. An agent can immediately tell what this tool does and how it differs.

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 is given: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts,' with concrete domains (financial verdicts, legal claims, medical lookups, public statements). It also states the tradeoff — 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups' — and names the alternative explicitly.

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