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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description adds valuable context beyond them: permanence of the deletion ('Permanently'), the exact cascade of what gets destroyed (share page and invites in addition to the project), and the ownership authorization requirement. No contradiction with annotations — in fact, the permanent-deletion language strengthens destructiveHint, and a delete is conventionally idempotent.

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 tightly packed clauses: the action with its full destruction scope, the confirmation requirement, and the ownership restriction. Every sentence earns its place, the core action is front-loaded, and there is zero 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 low-complexity tool with only 2 required parameters and an output schema present, the description covers everything an agent needs to invoke it correctly: what is destroyed, the confirmation gate, the authorization boundary, and permanence. Return values are handled by the output schema, and idempotency is declared by the annotations, so no critical information 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 50% — the confirm parameter already has 'Must be true' and const:true in the schema, but the description adds the missing why: 'Confirm with the user first' ties the boolean flag to a real-world consent gate. The id parameter is undocumented in both schema and description, but is made unambiguous by the tool name and the UUID format/pattern in the schema. The description meaningfully supplements the schema without fully covering the id semantics.

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 uses a specific verb ('deletes') against a precise resource ('saved project, its share page and invites'), naming the full scope of destruction. It clearly distinguishes from all 29 siblings — none of which perform deletion — so there is no ambiguity about which tool to pick.

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 explicit invocation conditions: 'Confirm with the user first' (only call after obtaining user consent) and 'Owner only' (only for the project owner). It provides clear context for when the tool is appropriate, though it does not explicitly name alternatives or when-not conditions — acceptable since no sibling tool handles deletion.

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