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

Annotations already cover destructive/idempotent hints, but the description adds genuine context beyond them: the invariant that a set must retain one screen, and the auth requirement (authorized Sonar account or write-scope API key). It doesn't disclose the rejection response shape, but with annotations carrying the safety profile this is solid.

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?

Three tight sentences, each earning its place: purpose, the constraint, and the auth requirement. Front-loaded with 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 single-parameter destructive tool with annotations covering safety, this covers purpose, a key invariant, and auth. The one missing piece is what happens on the last-screen rejection (error vs. no-op), but otherwise complete.

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% with the lone parameter (screenshot_id) already documented as 'Screen id to delete.' The description adds no format, syntax, or sourcing detail beyond what the schema provides, so the baseline 3 applies.

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?

Specific verb (delete) plus precise resource (one screen from a screenshot set). Distinguishes itself from siblings like sonar_delete_screenshot_set and sonar_update_screenshot by explicitly narrowing scope to a single screen.

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?

States a concrete precondition — a set must keep at least one screen, so deleting the last is rejected — which steers the agent away from invalid calls. Does not, however, point to alternatives (e.g. sonar_delete_screenshot_set) for removing everything.

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