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

Two sentences add real context beyond the annotations: 'A person reviews it' tells the agent the outcome is human-mediated rather than an automatic fix, and 'Changes no credits' rules out the cost concern an agent would otherwise have to check. However, it does not say whether the call blocks or returns a review ticket, whether it can be repeated (idempotentHint is false), or what a rejection looks like, so a mutation tool with no output-level explanation leaves gaps.

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 enumeration of report cases, followed by the identifier rule and the two behavioral facts an agent most needs. The telegraphic 'Changes no credits' phrasing is deliberate and costs nothing in clarity.

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, so return values need no explanation, and the description covers the trigger conditions, the dual identifier requirement, human review, and credit impact for a four-parameter tool. Only the follow-up lifecycle for a submitted report is left implicit.

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 75% schema coverage the baseline is already decent, and the description adds two things the schema does not: it clarifies the colloquial meaning of the 'artifact' enum value as 'a visible flaw', and it states the either/or rule for 'generation_id or receipt' that the schema's required list does not express. The 'details' free-text field is left unaddressed, but the schema documents it.

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 pairs a specific verb ('Reports') with a specific resource ('an image') and enumerates the failure classes it covers, mirroring the reason enum. It does not compare itself to the nearest sibling, submit_feedback, so an agent must infer the boundary between the two.

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?

It gives a clear trigger condition: use this when the image shows the wrong people, wrong place, a visible flaw, offensive content, or differs from the preview. It stops short of exclusions or naming alternatives such as edit_image or submit_feedback for cases that are not image-quality complaints.

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