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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds real value beyond that: success return shape, an explicit refusal taxonomy with named reasons, the refusal_cause sub-code semantics for llm_error, and the extra-LLM-call cost. Not a contradiction, and richer than the annotation baseline, but slightly over-specified in the refusal_cause parenthetical rather than fully clear about latency/limits.

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?

Front-loaded with the value proposition and differential ('Hallucination-resistant ... Same routing as ask_pipeworx'), then returns, then refusals, then when-to-use. Very dense and every sentence carries information, though the refusal_cause parenthetical ('wall' vs 'route'|'threw'|'unparseable'|'wall_after_failure') is the heaviest and most skimmable part.

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?

No output schema exists, so the description takes on the full burden of describing return values — and it does: exact success object fields (answer, evidence, confidence, source, fetched_at, refusal_reason) and every refusal variant. Together with the when-to-use guidance and cost note, an agent has everything needed to call and interpret it.

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% and the seven alias fields plus question and prefer_tool are all documented in the schema, so the baseline of 3 applies. The description notes that arguments are still filled from the question when prefer_tool is used ('Argument are still filled from your question'), which is a useful behavioral hint, but it never mentions the alias fields or prefer_tool's naming source (alternatives[]) that the schema carries.

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 mode (grounded, extraction-only answering) and explicitly contrasts it with sibling ask_pipeworx via 'Same routing as ask_pipeworx ... then EXTRACTS the answer using ONLY what the tool result contains'. The verb+resource ('answer a question from fetched tool data') is unambiguous and an agent can distinguish it from the routing-only sibling without opening a 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?

Gives an explicit trigger ('Use whenever an answer will be quoted, cited, or acted on ... financial verdicts, legal claims, medical lookups') and an explicit exclusion ('prefer ask_pipeworx for casual lookups'), plus the cost tradeoff ('Costs one extra LLM call') that drives the decision. This is the when/when-not/alternative triad in full.

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