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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is known. The description adds value beyond that with the authorization constraint ('Workspace owners only') and the semantic consequence of 'none' (project becomes hidden) and 'inherit' (falls back to workspace role). It does not disclose side effects such as audit logging or whether the last project owner can be demoted, which would push it to a 5.

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?

A single dense sentence that front-loads the core action and role domain before the authorization constraint. No redundant restatement of the title or schema.

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 3-parameter mutation with no output schema, the description covers the allowed values, their effects, and the caller requirement. It stops short of describing what happens on failure (e.g. missing project or non-existent user) or any guardrails around ownership, which leaves a small but real gap for a destructive operation.

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 67% and the two documented parameters only carry one-line labels ('The user id', 'The project id'). The description compensates by explaining what the role enum values actually mean, notably 'none (hidden)' and 'inherit' as a fallback to the workspace role — meaning the schema's bare enum does not convey.

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 ('Set a member's role on one project') and scopes it to a single project, which implicitly separates it from the workspace-level sibling set_member_role. The parenthetical gloss 'none (hidden)' makes the effect of the most ambiguous role value unambiguous.

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 prerequisite 'Workspace owners only' tells the agent who may call it, and mentioning that 'inherit' falls back to the workspace role hints at the relationship with set_member_role. However, it never explicitly says when to use this tool versus set_member_role or when to read state with get_project_access first, so the routing is left to inference.

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