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

Beyond the readOnly, openWorld, idempotent, and non-destructive annotations, the description discloses the exact success return shape, refusal reasons, and the behavior of refusing rather than inventing answers. It also reveals the cost tradeoff of one extra LLM call, adding valuable context not present in 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?

Every sentence earns its place: purpose, routing, output structure, refusal structure, usage guidance, and cost comparison. The description is dense but well-organized and front-loaded with the key differentiator.

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?

With no output schema, the description fully covers the success and refusal payloads, evidence behavior, and practical usage tradeoffs. Combined with the rich annotations, an agent has everything needed to decide when to invoke this tool and what to expect.

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 coverage is 100%, with every property already documented as an alias for 'question.' The tool description adds general context about routing and filling arguments, but offers no per-parameter details beyond what the schema already provides, so the baseline of 3 applies.

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 clearly identifies the tool as a 'Hallucination-resistant answer mode for high-stakes reads' with a specific behavior: it extracts answers using only tool result content. It also distinguishes itself from the sibling ask_pipeworx by emphasizing its grounded, evidence-backed nature.

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 states when to use this tool: 'whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts.' It also names the alternative ask_pipeworx and advises preferring it for casual lookups due to the extra LLM call cost.

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