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

Annotations already cover readOnly=true, openWorld, idempotent, non-destructive. The description adds substantial behavioral context beyond those: the exact success return shape {answer, evidence, confidence, source, fetched_at, refusal_reason:null}, the full refusal shape with all five refusal_reason enum values, the cost of one extra LLM call, and the guarantee that it refuses rather than invents when the data doesn't directly answer. 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?

The description is information-dense and front-loaded — the purpose predicate appears in the first phrase. It runs about three substantive sentences and includes two parenthetical lists (sample refusal reasons, domain examples). Every sentence earns its place; the return-format enumeration and refusal reasons are arguably verbose but valuable for a high-stakes tool. Slightly longer than strictly necessary, hence 4 rather than 5.

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 rightly compensates by fully specifying both return shapes (success and refusal, with refusal_reason values) and the evidence field semantics. For a tool whose input is a single natural-language question, the definition covers purpose, behavior, cost, return format, and when-not-to-use. Nothing an agent needs to invoke it correctly and interpret results 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 coverage is 100% — the question parameter and all five aliases (q, text, input, query, prompt) are fully documented in the input schema. The description adds no additional parameter-level detail, which is fine because the schema carries the full burden. Baseline 3 is appropriate when the schema does the heavy lifting.

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 the specific capability 'Hallucination-resistant answer mode for high-stakes reads' and states exactly what it does: same routing as ask_pipeworx, fetches data, then extracts the answer using ONLY what the tool result contains. It explicitly names its sibling ask_pipeworx as the faster non-grounded alternative, so an agent can distinguish them without opening either schema.

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?

Usage guidance is explicit and complete. It states when to use (whenever an answer will be quoted, cited, or acted on and facts must not be invented — with concrete domains listed: financial verdicts, legal claims, medical lookups, public statements) and when not to (casual lookups, citing the extra LLM-call cost). It names the alternative (ask_pipeworx) and the condition that selects it.

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