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

Annotations only cover the safety profile (readOnly, idempotent, openWorld); the description goes well beyond by naming the refusal taxonomy ('not_in_source'|'no_tool_match'|'tool_error'|'data_truncated'|'llm_error'), the success payload fields, and the latency/cost penalty versus the non-grounded sibling. It also discloses the internal pipeline (router over 7,115 tools across 1872 sources, then argument filling, then extraction), which is exactly the kind of context annotations cannot carry.

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 differentiator ('Hallucination-resistant answer mode for high-stakes reads') and the refusal enumeration is genuinely informative rather than padding. It is a dense single paragraph that reads slightly like a spec dump, but nearly every clause carries decision-relevant information.

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 compensates by enumerating the returned object fields (answer, evidence, confidence, source, fetched_at, refusal_reason) and the failure variants. For a read-only, one-required-parameter tool, an agent has everything needed to call it and interpret 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%, so the alias set and prefer_tool are already fully documented, making 3 the baseline. The description adds only indirect context — that routing picks a tool and fills arguments — without explaining prefer_tool semantics or the alias behavior, so it does not exceed the schema.

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 states a specific verb and resource — a grounded answer mode that routes, fetches, and extracts using only source text — and explicitly frames it as a variant of ask_pipeworx. An agent can distinguish it from the sibling without opening either schema, since the 'extracts using ONLY what the tool result contains' clause is the defining difference.

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?

It gives positive selection criteria ('use whenever an answer will be quoted, cited, or acted on... financial verdicts, legal claims, medical lookups, public statements') and an explicit exclusion routing to the sibling ('prefer ask_pipeworx for casual lookups'), reinforced by the stated cost tradeoff of one extra LLM call.

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