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

Annotations already declare readOnly=true and idempotent=true; the description adds substantial behavioral context beyond them: the grounding constraint ('using ONLY what the tool result contains'), the exact success return shape {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null}, and a full refusal contract with a refusal_reason enum covering five failure modes (not_in_source, no_tool_match, tool_error, data_truncated, llm_error). It also discloses the extra-LLM-call cost. 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?

Dense but every sentence earns its place: purpose, routing mechanism, success shape, refusal contract, when-to-use, and cost tradeoff each occupy one freighted clause. The core purpose is front-loaded before mechanics, and the refusal enum is compactly embedded rather than listed redundantly.

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 correctly takes on the return-contract burden — both success and refusal shapes are fully specified, including the refusal_reason enum. Combined with a 100%-covered input schema and safety annotations (readOnly, idempotent, non-destructive), an agent has everything it needs to invoke the tool correctly and interpret its results.

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% — all six properties (question plus the five aliases q, text, input, query, prompt) are documented in the schema itself, so the description doesn't need to carry param semantics. It adds only indirect guidance about question types via the named use cases (financial, legal, medical). Baseline 3 applies; 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?

Opens with a specific purpose statement — 'Hallucination-resistant answer mode for high-stakes reads' — then details the mechanism: routes across 5,743 tools/1500 sources, fills arguments, fetches data, and EXTRACTS the answer using ONLY the tool result. It clearly distinguishes itself from siblings by name ('Same routing as ask_pipeworx... prefer ask_pipeworx for casual lookups'), so an agent can tell it apart without opening the 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?

Explicitly states when to use: '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 also gives an explicit exclusion and names the alternative with its cost: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' Nothing is left to inference.

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