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

With no annotations provided, the description carries the full burden and does well: it discloses the asynchronous 'only stages a request' behavior, the browser review/approval step, and the owner-unrestricted rule. The warning about never accepting the PIN in chat is critical behavioral guidance that prevents agent misuse. This significantly exceeds minimum disclosure.

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 sentences, each serving a purpose: core operation, constraints, and approval-flow warning. It is front-loaded with the action and parameter selection guidance, and contains no filler. Efficiency without loss of critical information.

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 tool with no annotations and no output schema, the description covers all necessary invocation details: target identity, role null semantics, owner restriction, exact-one constraint, workspace scope, and the staged approval process. The only minor omission is a note about return/success response, but that is not essential for correct invocation. The definition is complete enough for an agent to call it correctly.

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%, so baseline is 3; the description adds value by imposing the 'exactly one of member or apiKey' exclusivity that is not enforced by the schema. It also reinforces that role=null means the workspace's default role, aligning with the schema description. The workspace param is left to the schema, which is acceptable.

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 opens with the specific action 'Move one member (by email) or one API key (by name) into an access role', naming the exact resource and operation. It distinguishes this from sibling role-manipulation tools (create_access_role, delete_access_role) and from set_member_workspace_role by focusing on assignment into an access role with the default-role null option.

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 provides explicit constraints on invocation: 'Give exactly one of member or apiKey', and clarifies that owners cannot be assigned a role. It also gives workflow guidance by explaining the request is only staged and that the owner must approve it in the browser, including the explicit 'Never ask for or accept the PIN in chat'. It does not name alternative tools, but the context is clear enough for an agent to decide when to use it.

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