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

Beyond the annotations, it discloses that the correction is persisted as a human override consumed by the triage list and digests, and — critically — that the call is proposed rather than executed, returning status='confirmation_required' with an action_id and plan_token until confirm_action is called. That execution model is not derivable from readOnlyHint/destructiveHint and materially changes how an agent must call it.

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?

Two tight sentences front-load the purpose and consequence, then a clearly separated confirmation block. The all-caps emphasis is slightly noisy but the content is dense and every line earns its place.

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?

The confirmation lifecycle is fully covered, which is the hardest part. But for a 4-parameter destructive mutation with zero schema descriptions and no output schema, the definition leaves message_id format and the optional summary/urgency semantics undocumented, so an agent still has to guess at half the inputs.

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%, so the description must compensate, and it does name the two semantically loaded fields (category, urgency) and their role. However, message_id (a integer|string union) and the optional summary string are never explained, and it doesn't say what happens to urgency if omitted or what an override does to a prior one.

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 gives a specific verb and resource ('Tell the classifier it got a message wrong — set the right category and urgency') and frames the result as a stored human override, which distinguishes it from manual mutation siblings like mail_label or mail_set_flag.

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?

The trigger is clear: use it when the classifier's category or urgency is wrong. It does not state exclusions, e.g. whether to prefer mail_label when the agent merely wants its own tagging rather than overriding the classifier, but the intended context is unambiguous.

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