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

Annotations already declare a safe read-only, idempotent, open-world operation, so the bar is lower — yet the description adds substantial behavioral context: the exact success return shape, the refusal contract with all five refusal_reason enum values, the guarantee that extraction uses only tool-result content, and the cost of one extra LLM call. This exceeds what annotations provide and fully discloses the tool's refusal behavior.

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 zero-waste prose: every sentence carries load — purpose, routing scope, extraction guarantee, success/refusal return contracts, use cases, and cost tradeoff. The core concept is front-loaded ('Hallucination-resistant answer mode for high-stakes reads'), and the return/refusal contracts are compactly encoded rather than repeated from structured fields.

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?

Since there is no output schema, the description correctly carries the full burden of explaining return values (answer, evidence, confidence, source, fetched_at, refusal_reason) and the failure mode (refusal with categorized reasons). Combined with 100% schema param coverage and safety-bearing annotations, nothing an agent needs to invoke or interpret this tool correctly 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?

Schema description coverage is 100%, so the baseline is 3 even if the description adds no parameter detail. The description does not explain the mode/question parameters further — it leaves that to the schema. It indirectly informs 'mode' by explaining when grounded mode matters, but it adds no format, alias, or value-level semantics beyond the schema. Baseline 3 is appropriate.

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, differentiating statement: 'Hallucination-resistant answer mode for high-stakes reads.' It names the resource (Pipeworx routing across 5,718 tools/1496 sources), a distinct behavior (extract answer using ONLY tool-result content), and explicitly positions itself against the sibling 'same routing as ask_pipeworx.' An agent can immediately distinguish this 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?

Provides explicit when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on,' with concrete domains (financial verdicts, legal claims, medical lookups, public statements). It also states when NOT to use it: 'prefer ask_pipeworx for casual lookups,' including the cost reason ('Costs one extra LLM call'). This is model usage guidance with a named alternative.

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