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

Annotations already declare readOnly=false, destructive=false, idempotent=false and openWorld=true, so the safety profile is covered. The description adds genuinely useful context (no cost, human review of every report) but says nothing about duplicate reporting behavior, what happens to the post in the interim, or any rate limit.

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?

Three short sentences, front-loaded with the action and then the two facts an agent actually needs (reason sourcing, no cost, human review). No filler.

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?

An output schema exists and annotations carry the safety profile, so return values and risk need no explanation. The remaining gap is the undocumented 'details' parameter and the unstated duplicate-submission behavior.

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?

With schema coverage at 50%, the description usefully reinforces that reason must be a category id from get_policy or the literal 'other', which is the trickiest parameter. The free-text 'details' parameter is undocumented in both schema and description, and post_id is left to inference, so it only partially compensates 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?

States a specific verb and resource with a qualifying condition: 'Report a post that breaks the policy.' The action is unambiguous and clearly not a read or delete, though it never explicitly contrasts with mutation siblings such as delete_post or cancel_post.

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?

Gives a trigger condition ('breaks the policy') and routes the reason parameter to get_policy, which implies a prerequisite lookup. It stops short of naming alternatives or exclusions, e.g., that removing your own post belongs to delete_post rather than here.

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