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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuinely new behavior: deletion propagates to every device (sync scope) and the currently open project is rejected. It stops short of stating reversibility explicitly, but the destructive hint covers that.

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. Scope (every device) is front-loaded, then the refusal condition and its remedies. No filler.

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?

Output schema exists, so return values need no explanation. For a destructive single-param tool, the description covers scope, id provenance, and the blocking precondition — everything needed to invoke it correctly.

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 0%, so the description must carry the param burden for projectId. It does add real meaning by naming the source of the id ('from list_projects'), but gives no format, prefix, or validity guidance. Partial compensation for a single undocumented parameter.

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+resource ('Delete a project') plus two distinguishing scopes: by id, and 'on every device'. An agent can distinguish it from update_project, list_projects, and open_project without opening any schema.

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?

Explicitly names the id source (list_projects) and an explicit when-not case: the open project is refused, with two concrete remediation alternatives (open_project, create_project). Nothing is left to inference.

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