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

Annotations already declare the safety profile (not read-only, non-destructive, non-idempotent, open-world), so the description's main addition is the word 'autonomous', which signals the agent files without human confirmation. That is useful, but it omits what happens after submission, whether a reviewer acts on it, and how duplicates are handled given idempotentHint=false.

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?

One sentence, front-loaded with the action and followed by the condition that justifies it. Nothing is padded or restated.

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 an open-world, non-idempotent write tool with no output schema, the description should say what the agent gets back or what happens next, and how to avoid duplicate reports. It covers the trigger but leaves the post-submission lifecycle and duplicate handling unexplained.

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 coverage is 100%, so the schema fully documents all four parameters and the enum. The description's examples (deceptive pricing, phantom stock, invalid coordinates) loosely hint at how to pick a category but never map them to the enum values, so baseline 3 applies.

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 ('Submit an autonomous trust-and-safety violation report') plus the triggering conditions, so it is immediately distinguishable from the transactional siblings (create_order, check_order_status, search_catalog). It stops just short of naming those siblings or restating the annotation title's framing.

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 an explicit trigger ('if a store exhibits deceptive pricing, phantom stock, or invalid coordinates'), which is more than most. But those three triggers cover only part of the enum (illegal_goods, harassment, other are unmentioned), and there is no statement of when NOT to file, whether to check for an existing report, or what alternatives exist.

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