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

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description discloses two non-obvious behaviors: it stores an immutable receipt (a persistence side effect) and meters one logical determination (a cost/accounting unit), plus the negative guarantee that no external repair is executed. That is real added context, though it omits whether the call fails or degrades when metering limits are hit.

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?

Two sentences, front-loaded with the diagnostic scope and followed by the side-effect/negative-guarantee clause. No filler, no repetition of the tool name, every clause carries information.

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?

For a tool with a nested request object, a 512 KiB body ceiling and an output schema already documenting return values, the description covers purpose, side effects and the no-repair guarantee adequately. The remaining gap is the missing routing relative to its three sibling tools and the evidence requirements.

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 only 50%, and the description supplies essentially no parameter meaning: it never explains the required evidence array, the schema constant, or the optional idempotency_key (despite the tool being idempotent). Only "candidate output" is echoed from the schema, so the description does not compensate for the coverage gap.

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 specific verb ("Diagnose") and resource ("a candidate output") and enumerates the exact defect classes checked: unsupported claims, contradictions, wrong attribution, stale authority, unsafe execution claims. It implicitly separates itself from the repair siblings by stating it "does not execute an external repair," but never names fahce_integrity_repair_bundle, fahce_plan_bounded_repair, or fahce_verify_repaired_output, so an agent must infer the boundary.

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?

Usage is only implied: by saying it stores a receipt and does not perform repair, the description suggests this is the diagnostic step preceding repair. There is no explicit when-to-use statement, no condition that selects it over fahce_verify_repaired_output or fahce_plan_bounded_repair, and no prerequisites (e.g., evidence must be supplied) spelled out.

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