Unmark evidence

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

The description adds valuable behavioral context beyond the annotations: it discloses the 403 evidence_frozen edge case and instructs not to retry. This complements readOnlyHint=false and destructiveHint=false by explaining how the system behaves in a specific state. It does not contradict the 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?

The description is two sentences with no filler. The first sentence immediately states the action and permission, and the second sentence delivers a crucial error-handling nuance. Every clause earns its place.

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 simple mutating tool with no output schema, the description covers the essential operational details: what is removed, who can do it, and a critical failure scenario with explicit guidance. The one minor gap is that it does not describe the expected success response, but for a low-complexity action this is not a significant omission.

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?

The schema already describes both parameters fully, with id as a UUID and kind as an enum of 'comment' or 'file.' The description echoes 'comment or case file' but adds no meaning beyond what the schema provides. Baseline 3 is appropriate given the 100% schema description coverage.

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 verb and resource: 'Remove an evidence mark from a comment or case file.' This clearly identifies the operation and differentiates it from sibling tools like tribeunal_mark_evidence and tribeunal_list_evidence. The permission qualifier '(case owner or jury members only)' adds further precision.

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 clear context for when the tool is applicable: only for case owners or jury members, and it explicitly warns that on arbitration-mode cases, once the case leaves open, the evidence record freezes and 403 evidence_frozen means the record is closed rather than a permission failure. It does not name specific alternative tools, so it falls short of a 5, but the guidance is strong.

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