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

Annotations already declare readOnly, idempotent, open-world, and non-destructive — the description adds substantial behavior beyond them: the refusal protocol with five enumerated refusal_reason values, the evidence-grounded guarantee (verbatim quote), the success return shape, and the extra-LLM-call cost implication. It fully documents the failure contract, which is exactly the kind of behavioral disclosure an agent needs and that annotations cannot convey. No contradiction with 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?

Every sentence earns its place: mode definition, mechanism, success contract, refusal contract, usage criteria with examples, and cost-based routing recommendation. It is front-loaded with the key differentiator and contains no filler or redundancy. The length is justified by the complexity of the behavioral contract that must be conveyed in the absence of an output schema.

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?

With no output schema, the description fully compensates by specifying both the success response shape (answer, evidence, confidence, source, fetched_at, refusal_reason:null) and the failure shape with enumerated reasons. It explains when to use it, the cost trade-off versus the alternative, and the routing mechanism. Nothing an agent needs to decide whether to invoke it or interpret its result 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% — the schema already documents the question parameter and all five aliases, so the baseline is 3. The description adds contextual color by explaining the question gets routed across 5,798 tools and 1,517 sources, but it does not add syntactic or format-level parameter details beyond the schema. The schema carries the load; the description's marginal contribution is the routing context.

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 mode name ('Hallucination-resistant answer mode for high-stakes reads') tied to a clear verb+resource (ask_pipeworx). It distinguishes itself from the sibling ask_pipeworx by specifying the unique mechanism: extracting the answer using ONLY the tool result content, with an explicit evidence/refusal contract. 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 guidance is given: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts,' followed by concrete domains (financial verdicts, legal claims, medical lookups, public statements). It also names the alternative with a condition: 'prefer ask_pipeworx for casual lookups,' including the cost-based rationale (one extra LLM call). This is complete routing guidance with no inference needed.

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