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

Beyond the readOnly/idempotent annotations, the description fully discloses the success return shape ({answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null}), every refusal mode with an enumerated refusal_reason, and the concrete cost/latency tradeoff (one extra LLM call). For a tool with no output schema, this level of behavioral disclosure is exactly what the description must 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?

The description is dense but front-loaded with the core purpose, and every sentence earns its place: mode, mechanics, success shape, refusal shape, use cases, and cost tradeoff. It is longer than the minimum because it substitutes for a missing output schema; the refusal_reason enumeration is slightly verbose but functionally necessary.

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?

Despite having no output schema, everything an agent needs to call and interpret this tool correctly is present: routing behavior, success versus refusal contracts, failure reasons, evidence semantics, and the tradeoff against the sibling. The trivial one-question input schema and safety annotations are fully covered. Nothing material 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% — all six parameters are documented aliases of 'question' with a clear natural-language definition, so the schema does the heavy lifting. The description adds mild context by noting the tool 'fills arguments' internally during routing, which clarifies the user only supplies a plain question, but it doesn't add parameter syntax or format details beyond the schema. Baseline 3 is correct.

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 opening phrase 'Hallucination-resistant answer mode for high-stakes reads' names a specific verb, resource, and scope. It explicitly differentiates from the sibling ask_pipeworx by the grounded-extraction behavior: 'EXTRACTS the answer using ONLY what the tool result contains' versus inventing facts. An agent can immediately tell this apart from ask_pipeworx and ask_pipeworx_beta.

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 conditions ('whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts — financial verdicts, legal claims, medical lookups, public statements') and an explicit when-not-to-use with the named alternative ('Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups'). This is textbook routing guidance.

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