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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent, closed-world mutation, so the safety profile is partly covered. The description adds no behavioral context: it does not explain the 'reviewed' state it claims to create, side effects, permissions required, or what happens on a duplicate call.

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?

A single short sentence with the action front-loaded and no filler. It is efficient, though it is under-specified rather than deliberately concise.

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 mutation tool with no output schema, three undocumented parameters, and no annotations covering permissions or effects, the description should carry far more weight. It omits required-parameter expectations, the 'reviewed' semantics, and any result/shape information.

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 0% for all three parameters (name, project_id, description), so the schema offers no semantic help. The description only weakly implies project_id and does not describe name or description at all, failing to 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 states a specific verb+resource ('Create a reviewed evidence collection') and scopes it to a project, which separates it from siblings like create_project, create_claim, and add_evidence_to_collection. It stops short of explicitly contrasting with those siblings or clarifying what 'reviewed' means, so it is clear but not fully differentiated.

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?

There is no guidance on when to use this tool versus the many sibling creation tools (create_project, create_claim, add_evidence_to_collection) or whether a project must already exist. The agent must infer usage entirely from the name and the mandatory project_id.

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