create_incident

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent write. The description adds the propagation behavior of the incident onto status pages, which is real context beyond the annotations. It omits auth/permission needs, whether duplicate incidents are possible (relevant given idempotentHint=false), and whether notifications are dispatched.

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 short sentences with zero filler; the scoping behavior is front-loaded immediately after the core action.

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 7-parameter tool with no output schema and 29% schema coverage, the description covers the monitor-scoping decision but leaves most parameters and the return value (incident id/handle) unexplained. Adequate but with visible gaps an agent may trip over.

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 only 29% (project and workspace only), so the description must compensate but largely does not. Effectively it explains monitorId's semantic effect and confirms it is optional, but severity, visibility, body, and title limits are left undocumented in both places.

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 ('Open a manual incident') and clarifies the 'manual' nature versus system-generated incidents. It does not name any sibling tool (e.g., update_incident or post_incident_update) to disambiguate the lifecycle stage, but the action itself is unambiguous.

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 description gives a usable decision rule for the monitorId parameter: with a monitor the incident appears on status pages containing that monitor, without one it appears project-wide. However, it offers no guidance on when to prefer this over post_incident_update or update_incident, nor any prerequisites such as permissions.

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