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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), yet the description adds substantial context beyond them: the two-stage routing+extraction behavior, the exact success payload shape, an enumerated set of refusal reasons, the 'refusal_cause' sub-taxonomy for llm_error including the meaning of 'wall', and the extra-LLM-call cost. The only shortfall is that latency/rate-limit behavior of the underlying tool fetch is not characterized, so it lands just under the top.

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 lead sentence front-loads the differentiator ('Hallucination-resistant answer mode for high-stakes reads') before the mechanics, and the final sentence front-loads the cost tradeoff. The long middle sentence packs the payload shape, refusal taxonomy, and refusal_cause semantics densely, but every clause carries distinct information an agent would otherwise have to guess.

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 carries the return-contract burden itself, and it does so completely: exact success fields (answer, evidence, confidence, source, fetched_at, refusal_reason:null) and the full refusal enumeration with the llm_error sub-cause mapping. For a single-required-parameter, open-world query tool, nothing an agent needs to call or interpret it 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% and it fully documents the question aliases and prefer_tool override (including the 'unknown names are refused, never guessed' rule), so the baseline is 3. The description adds only indirect meaning: 'picks the right tool from 7,188 ... fills arguments' tells the agent the question is auto-routed and arguments are auto-generated, which contextualizes prefer_tool, but it never names prefer_tool or explains the override path itself.

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 ('EXTRACTS the answer using ONLY what the tool result contains') and frames the tool's identity as a hallucination-resistant answer mode that shares routing with ask_pipeworx. It clearly separates this tool from ask_pipeworx (casual lookups) and implies a distinction from ask_pipeworx_beta and validate_claim by naming the routing+extraction two-stage flow.

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 explicitly names the trigger condition ('whenever an answer will be quoted, cited, or acted on') with concrete examples (financial verdicts, legal claims, medical lookups, public statements), and names the alternative for the other case ('prefer ask_pipeworx for casual lookups'). Both the when and the when-not, plus a cost tradeoff, are spelled out.

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