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

Goes far beyond the readOnlyHint/idempotentHint/openWorldHint annotations by disclosing the refusal contract: exact refusal_reason enum values ('not_in_source'|'no_tool_match'|'tool_error'|'data_truncated'|'llm_error') and the guarantee that answers are extracted ONLY from what the tool result contains. It also reveals the full success return shape and the extra-LLM-call cost, neither of which annotations convey. 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, return contract, refusal contract, usage guidance, and cost trade-off are all present with zero filler. The detailed return/refusal shape must live in the description because no output schema exists. The most actionable facts (cost, when-not-to-use) are clearly flagged at the end without burying the purpose.

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?

For a tool with no output schema, the description carries the full return contract — six success fields and five distinct refusal reasons — so nothing an agent needs to interpret the result is missing. The unusual routing complexity (5,798 tools across 1517 sources) is explained in one clause. Sibling differentiation, safety profile via annotations, and cost semantics are all covered.

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% — the `question` parameter is fully documented in the schema, including its five aliases (query, q, prompt, text, input), so the high-coverage baseline of 3 applies. The description adds usage-oriented context about which questions merit this mode but no new parameter-level syntax or formatting details. The schema is doing the work here, which is acceptable.

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 purpose — a 'hallucination-resistant answer mode for high-stakes reads' that extracts answers using ONLY tool-result content and refuses rather than fabricate. It explicitly distinguishes itself from sibling ask_pipeworx ('Same routing as ask_pipeworx') by adding the extraction step and the refusal contract. The verb+resource pairing is unambiguous: answer a question, grounded in fetched tool data.

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 it — 'whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' — followed by concrete domains (financial verdicts, legal claims, medical lookups, public statements). It names the alternative directly ('prefer ask_pipeworx for casual lookups') and discloses the causal cost difference of one extra LLM call. This is the clearest possible when/when-not routing guidance.

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