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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, destructiveHint=false, so the safety profile is covered. The description goes far beyond: it discloses the exact success return shape ({answer, evidence, confidence, source, fetched_at, refusal_reason:null}), the full refusal contract with enumerated reasons (not_in_source, no_tool_match, tool_error, data_truncated, llm_error), and the grounding guarantee that the answer is extracted 'using ONLY what the tool result contains.' The refusal contract is especially valuable — an agent knows to treat a null answer as a truthful negative rather than a failure. This is exemplary behavioral disclosure.

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?

Three dense sentences with zero waste. The core identity ('Hallucination-resistant answer mode for high-stakes reads') is front-loaded, followed by mechanism, then the behavioral contract, then usage guidance and cost tradeoff. The refusal-reason enum and return shapes are technical but necessary — an agent must know both success and refusal shapes to interpret results. Every clause earns its place; nothing is filler.

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 bears the full burden of explaining return values — and it does so exhaustively for both success and refusal paths, including why refusals occur. For a tool this complex (routing across 5,743 tools), the description covers mechanism, cost, alternatives, grounding guarantee, and both output contracts. An agent has everything needed to call it correctly and interpret any outcome. No meaningful gap remains.

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 baseline of 3 applies — the schema already documents 'question' with aliases (q, text, input, query, prompt) and describes it as natural-language input. The description adds context about what happens to the question (routed, arguments filled, data fetched) but no parameter-level syntax or format guidance beyond the schema. The description neither compensates further nor falls short of the baseline.

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 verb-context pairing — 'hallucination-resistant answer mode for high-stakes reads' — and explains the exact mechanism (routes through 5,743 tools, fetches data, extracts answer from tool output only). It explicitly differentiates from siblings: 'Same routing as ask_pipeworx' plus 'prefer ask_pipeworx for casual lookups' tells the agent how this differs from its near-namesake. An agent can distinguish ask_pipeworx_grounded from ask_pipeworx and ask_pipeworx_beta without opening schemas.

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 explicit when-to-use guidance ('Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts') with concrete high-stakes domains (financial verdicts, legal claims, medical lookups, public statements). It also names the alternative and the washout condition: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' Both selection and exclusion criteria are stated, leaving nothing to inference.

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