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

Annotations already declare destructiveHint and idempotentHint, but the description adds context the annotations cannot express: the cascade scope (tasks, assignments, status history), the administrator permission requirement, and the absence of any undo. These are exactly the facts an agent needs to decide whether calling is safe.

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 with the most alarming fact (DESTRUCTIVE, cascade) front-loaded, followed by the access constraint and irreversibility. Every clause carries decision-relevant information with nothing repeated.

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?

Given one parameter, no output schema, and annotations already covering the safety profile, the description covers what is destroyed, who may do it, and that it is irreversible. It stops just short of saying whether a trashed project can still be recovered via list_trash or what happens to dependent entities outside the project.

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% for the single required 'id' parameter, so the schema already documents the input fully. The description adds no format, range, or lookup guidance beyond that, which is the baseline case for a fully documented single 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 and resource ('permanently delete a project') and immediately defines scope with 'ALL of its tasks, assignments, and status history (cascade)', which distinguishes it from the sibling delete_task and purge_task. An agent knows exactly what this tool removes without opening the 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?

Usage is only implied through the 'Administrator only' prerequisite and the 'no undo' warning. It never says when to choose this over related tools (delete_task, clear_project_baseline, or any trash/restore path), so an agent must infer the decision boundary.

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