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

Annotations provide no behavioral hints (all false), so the description carries the full burden. It discloses that the tool modifies state by persisting the finding and justification in the immutable EDL version's durable record, and that it is project-scoped. It also states the return value (project identity with its result). This is strong disclosure, though it could be more explicit about the irreversibility of the action, which is implied by 'durable record.'

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 efficient, front-loading the critical project scope and then layering conditions, effects, and exclusions. Every sentence adds unique information with no fluff or redundancy. The structure flows logically from scope to usage to persistence to exclusions.

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 explains the return value ('returns the project identity with its result'). It also covers the key behavioral context: project scoping, persistence, and the requirement for direct evidence. It doesn't mention potential error conditions or side effects on other projects, but the project-scoped statement implies isolation. Overall, it gives an agent enough to correctly decide when to call 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 description coverage is only 25%, so the description must compensate. It emphasizes that project_id must be explicit and copied from list_projects/open_project/project_state, which is also in the schema. It does not explain the semantics of finding_ids or evidence_ids, and it does not clarify how justification should be structured beyond the schema's minLength. The description adds minimal value beyond what the schema already provides.

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 states the tool's function: it justifies verification findings for a specific project. It explicitly says it acts only on the explicit project_id and returns the project identity with the result. It also distinguishes itself by stating that certain conditions (missing previews, caption proof, corrupt glyphs, invalid music timing) cannot be justified, which differentiates it from repair-oriented siblings.

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 gives explicit when-to-use guidance: 'Resolve a genuine verification false positive only after direct pixel/audio evidence proves it.' It also provides clear when-not-to-use exclusions: 'Missing previews, caption proof, corrupt glyphs and invalid music timing require repair and cannot be justified.' This effectively routes the agent to the correct action without ambiguity.

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