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

Beyond the annotations (destructiveHint=true, idempotentHint=true), the description discloses cascade scope ('all its screens') and irrecoverability ('Designs cannot be recovered'), plus the human-confirmation workflow required before invoking. These are consequential traits the structured hints do not convey.

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?

Four short sentences, front-loaded with the irreversible action and scope, then the guardrails. Every sentence earns its place with no redundancy or 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?

For a destructive two-parameter tool with an output schema and full annotation coverage, the description supplies everything needed: scope, irreversibility, and the confirmation gate. No gaps remain for correct invocation.

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 100%, so projectId and confirm are already fully documented in the schema, and the description adds no syntax or format detail beyond it. Per the rubric, full schema coverage sets the baseline at 3.

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 states a specific verb and resource ('Permanently delete a project') and adds blast radius ('and all its screens'), so an agent immediately understands the operation. No sibling tool performs deletion, so it is clearly distinguished from create_project, get_project, and list_projects.

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?

It gives explicit preconditions ('Call only after your user confirms the exact project by name') and an explicit prohibition ('Never delete projects to tidy up on your own initiative'). Both the when and the when-not are spelled out, leaving nothing to inference for a high-risk operation.

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