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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds real substance beyond them: the deletion is a cascade covering responses, there is no undo, and no export is possible afterward. Those consequences are not derivable from the annotation flags and directly inform agent behavior.

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 'Destructive:' signal, then the irreversibility, then the mitigation. No filler and the most important information comes first.

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 single-parameter destructive tool with a well-covered schema and no output schema, everything an agent needs to decide and act correctly is present: severity, cascade scope, irreversibility, and a pre-call caution.

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% and the single project_id parameter is already documented with its provenance ('from list_projects or create_project'). The description adds no parameter-level detail, so the baseline 3 applies.

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 adds scope by naming the cascade target ('and its responses'). The word 'permanently' plus the cascade clause distinguishes it from sibling operations like close_project or delete_block 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 a clear conditional guideline: 'Read the responses first if they matter.' That tells the agent when to hesitate before calling. It stops short of naming alternatives (e.g., close_project for a reversible option, get_project/list_responses as the read path), which would be the 5-level answer.

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