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

Adds substantial context beyond the annotations (destructiveHint=true, openWorldHint=true, idempotentHint=false): the change is PUBLIC even when publish=false, publish=true fans out to email/SMS/Slack/Teams/X with possible vendor charges, and listed components are marked degraded publicly. 'Starts in the investigating state' is a behavioral detail no structured field carries.

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 'WRITE:' and the core action, and nearly every sentence carries operational weight. There is mild redundancy — public visibility is asserted twice ('These changes are PUBLIC... including publish=false' and 'on the PUBLIC page') and the publish explanation largely restates the schema — but the density is justified for a destructive, public-facing write.

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 6-parameter destructive write with no output schema, the description covers the essentials an agent needs before calling: public exposure, subscriber fan-out and charges, component degradation side effect, initial state, and an approval prerequisite. Nothing material is missing.

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 meaning by stressing that publish is a broadcast switch, not a privacy switch ('does not make a private draft' — echoed in the schema but framed as a caveat) and by naming the downstream subscriber/integration effects and cost. It does not clarify component_ids format or initial_comment beyond 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?

Opens with a specific verb and resource ('WRITE: open an incident (an unplanned notice) on the status page') and parenthetically pins the notice type, which cleanly separates it from sorryapp_create_maintenance (planned) and sorryapp_create_notice_update (updates to an existing incident). The trailing API mapping (POST /v1/pages/{page_id}/notices with type=unplanned) removes any ambiguity.

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 a real usage gate: 'Confirm the content and audience first,' reinforced by the required confirm parameter, and explains when to set publish=true versus false. It does not explicitly name the sibling to use for planned maintenance, so the routing to alternatives is implied by 'unplanned' rather than stated.

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