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

Annotations already establish read-only, idempotent, open-world, and non-destructive traits, so the baseline bar is lower. The description adds substantial behavioral context beyond annotations: it explains the extra LLM call cost, the strict grounding constraint ('using ONLY what the tool result contains'), the exact success return shape, and the specific refusal_reason enum values. This gives full visibility into how the tool behaves in edge cases, which annotations alone would not convey.

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 compact but information-dense, starting with the most salient phrase ('Hallucination-resistant answer mode') and then layering routing, extraction, return values, refusal reasons, usage context, and cost trade-off. Every sentence serves a purpose — no filler, no repetition of schema fields. Despite its length, the structure makes the content scannable and front-loaded.

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?

Because there is no output schema, the description fully explains return values and refusal reasons — that is essential context for an agent to interpret results. It also covers the routing rationale, cost, and use case boundaries. The only parameter is well-documented in the schema, and the behavioral traits are covered by annotations plus the description. Nothing critical is missing for an agent to select and invoke this tool correctly.

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 with aliases (question, query, q, prompt, text, input). The description adds no additional meaning about the parameter itself, which is acceptable because the schema already carries the burden. Per calibration, a baseline of 3 is correct when schema coverage is high and the description doesn't need to compensate.

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 opens with a concrete, distinctive purpose: 'Hallucination-resistant answer mode for high-stakes reads.' It then details the behavior — routing to a source tool, fetching data, and extracting an answer strictly from results — which is far more specific than a generic 'answer questions' phrasing. It also explicitly contrasts with the sibling ask_pipeworx ('Same routing as ask_pipeworx'), so an agent can tell them apart immediately.

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?

The description provides explicit when-to-use guidance: 'Use 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).' It also gives a clear exclusion and alternative: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' This is exactly what an agent needs to route between the two modes.

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