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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive hints, and the description adds substantial behavioral context: it guarantees extraction 'using ONLY what the tool result contains,' describes the exact success and refusal return shapes, enumerates refusal reasons, and discloses the extra LLM call cost. This goes well beyond the structured annotations and makes the tool's degeneracy behavior explicit.

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?

Although the description is relatively long, every sentence carries operational weight: core mode, routing behavior, return contract, refusal contract, use cases, and cost tradeoff. The essential purpose is front-loaded in the first sentence, and the rest is dense, structured information rather than filler. This is appropriate for a high-stakes tool where agent decisions depend on understanding refusal behavior.

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 compensates by fully specifying the success response shape and all refusal variants. It also covers usage context, cost, and the boundary with ask_pipeworx. For a question-answering tool with one required parameter and complete alias documentation, nothing an agent needs to invoke it correctly 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 as aliases for the single required 'question' field. The description does not add parameter-level semantics beyond this, but it does not need to because the schema fully covers the input contract. Baseline 3 is appropriate when the schema handles parameter documentation completely.

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 purpose—'Hallucination-resistant answer mode for high-stakes reads'—and clearly differentiates it from ask_pipeworx by explaining it uses only tool-result content to extract answers. It also identifies the sibling it parallels ('Same routing as ask_pipeworx') while distinguishing the grounded behavior. This is a precise, non-tautological definition.

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 explicitly says when to use this tool: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts.' It also gives a concrete exclusion: 'prefer ask_pipeworx for casual lookups.' It names the alternative tool and the cost tradeoff, leaving no ambiguity about routing.

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