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

Annotations already disclose readOnlyHint=false and destructiveHint=true, and the description usefully adds that the saved report is redacted, that a notification is queued to AdsAgent support, and that credentials/customer data must never be included. It does not describe failure behavior or what the response contains, but it meaningfully fleshes out the side effects the annotations only flag.

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?

Four short sentences, front-loaded with the action and its routing trigger, then idempotency and the safety constraint. Every sentence carries either selection or invocation information; no filler or repetition of the title.

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, non-idempotent-by-default reporting tool with no output schema, the description covers purpose, trigger, retry semantics, and data-handling constraints. The remaining gap is parameter-level coverage of the seven required fields, which the schema leaves entirely undocumented.

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 description coverage is 0% across 8 parameters (5 of them enums), so the description carries the burden and only partly compensates: it explains support_ref's provenance and idempotency_key's reuse semantics, but says nothing about submission_mode, task_stage, user_impact, observation_code, client, or connection_context. The enum values are largely self-describing, keeping this at a minimum-viable 3.

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 concrete verb+resource ('Submit an error or incorrect-data report') and its scope ('using the most recent support_ref'), which is clearly separable from the sibling support_get_report_status. It stops short of explicitly contrasting itself with that status-checking sibling, so it is clear but not fully differentiated.

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 trigger condition: 'Use after two repeated failures or a user's data discrepancy,' plus a retry rule ('Reuse the same idempotency_key when retrying'). It does not name an alternative tool or state when not to file a report, so the routing guidance is contextual rather than exhaustive.

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