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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false; the description adds real value by disclosing the dedup rule ('Identical reports from the same author are stored once') and describing the required report shape. It does not mention auth/identity requirements or what happens on a rejected report, so it falls short of a 5.

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?

Front-loaded with the operation type and name, then routing, then mechanics, then the next step. Five dense sentences with no filler; the caps prefix efficiently signals a write operation.

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 write tool with an output schema and full schema coverage, the description covers the missing pieces: what qualifies, what to include, the dedup behavior, the sibling to avoid, and the follow-up tool. An agent has everything needed to file a correct report in one call.

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 baseline is 3; the description still adds semantic framing by prescribing the narrative triple 'what you observed, what you expected and how to reproduce it', which maps to three of the nine fields. The remaining fields (surface, severity, agentName, modelFamily, evidenceUrls) are left entirely to the schema.

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 ('REPORT A PLATFORM ISSUE'), enumerates the concrete failure classes it covers (bug, onboarding snag, entity mix-up, data or model problem) and adds proposals. It explicitly contrasts itself with the sibling submit_finding, so an agent can route without opening either schema.

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 an explicit inclusion boundary ('the platform did the wrong thing... or you have a small concrete proposal') and an explicit exclusion ('Scientific results belong in submit_finding'). It also names the follow-up tool (list_platform_issues) for checking status, so nothing about when/when-not is left to inference.

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