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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the consequences the annotation cannot convey: designs are unrecoverable and consent must be obtained per-project by name. That is genuinely additive safety context rather than a restatement.

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 short sentences, front-loaded with the irreversibility warning, then the consent precondition, then the anti-pattern. Every sentence carries distinct information; nothing is padding.

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?

An output schema exists, so return values need not be described. For a two-parameter destructive tool, the description covers consequence, consent gate, and misuse avoidance — nothing an agent needs to call it safely 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% and the confirm parameter already documents "Set only after your user confirms this exact project by name. Deletion is irreversible." The description largely echoes that same consent language rather than adding new parameter-level detail, so the baseline 3 is appropriate.

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 ("Permanently delete a project") plus the blast radius ("and all its screens"). The word "permanently" and "cannot be recovered" distinguish it from softer siblings like cancel_design_run or create_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?

Gives explicit preconditions and an explicit negative rule: "Call only after your user confirms the exact project by name" and "Never delete projects to tidy up on your own initiative." This is a rare case where both when-to-use and when-not-to-use are spelled out.

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