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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is known. The description does add one non-obvious trait beyond the annotations: the action also resolves the corresponding review-queue item. It omits whether the action triggers a webhook event, whether it can be undone, and what happens if the item is already resolved.

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 short sentences, front-loaded with the action, no filler. The first line merely echoes the title and tool name, which is mild redundancy but harmless.

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 destructive mutation with no output schema, the description covers what it does and one side effect (queue resolution) but not the return shape, failure modes, or whether a webhook fires. Adequate to call it, not enough to call it confidently in edge cases.

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 description contributes no parameter meaning at all. However, the input schema itself carries per-field descriptions for id, reason, queueId, moderator, createCasebookCase and projectId, so the agent is not left blind — the baseline of 3 applies since the schema does the heavy lifting.

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?

States a specific verb+resource ('Reject a content item') and adds a concrete effect: it uses the built-in reject action and resolves the item in the review queue. It does not distinguish itself from the obvious counter-tool content-allow or from queue-items-resolve, which handle adjacent decisions.

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?

No guidance on when to reject versus allow, versus resolving a queue item directly, or what prerequisites (project key, moderator identity) are needed. The agent must infer the whole decision context from the sibling list.

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