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

Annotations already flag destructiveHint=true, and the description adds meaningful behavioral detail beyond that by revealing that the action 'Revokes your project keys' and that owners cannot perform this action. This gives the agent useful context about side effects and eligibility without contradicting the annotations.

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 deliver the core action, an important restriction, a side-effect warning, and routing to an alternative. There is no filler, and the most important scoping information is front-loaded.

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 mutation tool with destructiveHint=true, the description fully covers who can use it, what happens, what cannot happen, and which sibling should be used instead. The absence of an output schema is not a gap here because the behavioral notes are sufficient 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 coverage is 100% and the parameter has its own description, but the tool description adds semantic value by specifying that the project_id must refer to a project the user was invited to. That narrows the acceptable values beyond the schema's generic 'from create_project or list_projects' guidance.

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 clearly states a specific action: leaving a project the user was invited to, and explicitly scopes it with 'Owners cannot leave'. It differentiates from the sibling tool remove_project_member by naming it directly as the alternative for owner-removing-someone-else scenarios.

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 explicitly states when this tool is appropriate ('a project you were invited to') and when it is not ('Owners cannot leave'). It also names the alternative tool, remove_project_member, and the exact condition that should trigger that alternative.

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