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

Annotations already declare readOnly/openWorld/idempotent, so the bar is lower, but the description adds substantial behavioral context beyond them: the exact success contract ({answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null}), the explicit refusal shape, and the full refusal_reason enum ('not_in_source'|'no_tool_match'|'tool_error'|'data_truncated'|'llm_error'). It also discloses the extra LLM call cost. No contradiction with annotations — the read-only, open-world, idempotent hints are consistent with a fetch-and-extract read operation.

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?

Dense but every sentence earns its place: purpose, mechanism, success contract, refusal contract, usage cases, and cost tradeoff are each covered once. It is front-loaded with the core differentiator and structured so an agent can skim from 'what' to 'return' to 'when'. Slightly long, but no redundancy.

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?

There is no output schema, so the description correctly bears the burden of explaining return values — and it does so completely, enumerating both the success shape and all five refusal reasons. Routing scale (5,908 tools / 1,540 sources), the anti-hallucination guarantee, and the cost delta versus the sibling are all disclosed, leaving nothing material missing for a tool of this complexity.

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% — all six parameters are documented aliases ('Accepts query, q, prompt, text, input as aliases') — so the schema already carries the full parameter burden. The description adds no per-parameter meaning beyond what the schema provides, which matches the high-coverage baseline of 3.

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?

States a specific verb and resource with a sharp differentiator: 'Hallucination-resistant answer mode for high-stakes reads.' It explicitly contrasts with the sibling ask_pipeworx ('Same routing as ask_pipeworx ... then EXTRACTS the answer using ONLY what the tool result contains'), so an agent can tell this apart from ask_pipeworx and ask_pipeworx_beta without opening schemas.

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 and when-not-to-use guidance: '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 names the alternative (ask_pipeworx), gives the selection condition ('prefer ask_pipeworx for casual lookups'), and discloses the cost tradeoff ('Costs one extra LLM call').

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