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

Annotations already mark the operation as idempotent and non-destructive, but the description adds precise behavioral detail: the specific error report 'not_a_member', the fact that the project remains visible workspace-wide, and that leaving a non-member project changes nothing. This goes beyond the annotations and gives the agent an accurate model of side effects.

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?

The description is three concise sentences, each carrying essential information: primary effect, non-effect on the project, and the edge-case behavior. No filler or redundancy, and the most important outcome 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 simple, non-destructive operation, the description covers what the tool does, what it leaves untouched, and the error behavior for non-members. An output schema exists and the input schema covers parameter details, so nothing an agent needs to call the tool correctly 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?

The input schema has 100% parameter description coverage, so the schema already documents each parameter. The tool description does not add further parameter-level detail or nuance, which matches the baseline of 3 for fully documented schemas.

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 names a specific verb ('Leave') and resource ('a project') and states the concrete effect: removal from the caller's 'Your projects' sidebar list. It also explicitly clarifies what the tool does not do — the project itself is untouched and remains visible to the workspace — which cleanly distinguishes it from destructive project operations.

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?

It provides clear context for when this tool is appropriate: the goal is to remove a project from the caller's personal sidebar, not to alter the project itself. The boundary case of leaving a project the caller is not in is also described. However, it does not explicitly name alternatives like project_join or state when not to use this tool.

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