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

The description is unusually generous about real behavior: what is preserved on block (role, folders, note, API settings, seat), what stops working (dashboard, API, MCP, member API key), and the precondition set. However, "Repeating the same state is a success without changes" describes idempotent semantics while the annotations declare idempotentHint=false — a real though non-safety-critical mismatch. It also softens destructiveHint=true by stressing that nothing is deleted, which is arguably correct for an access toggle but leaves the agent to reconcile the two.

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?

Front-loaded with the action, then effects, then exclusions, then the permission requirement — a sensible order with no filler sentences. The second sentence is a long semicolon chain and could have been split, but every clause carries distinct information (seat retention, key invalidation, idempotency).

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, non-read-only mutation with no output schema, the description covers effect, side effects on credentials, preconditions, and authorization. The main omission is return behavior — it never says what a successful call returns or whether the change is reflected in get_workspace_members — which matters since no output schema exists.

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 schema already spells out the boolean polarity ("true — close access, false — restore it") plus where member_id and workspace_id come from. The description adds consequences of the flag but no parameter-level syntax or edge cases beyond the schema, so it neither compensates for nor needs to compensate for a gap.

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?

Opens with a precise verb+resource pair and immediately scopes it: "Closes a member's access to the account without removing them, or gives it back." That "without removing them" clause distinguishes it from remove_workspace_member, and "access" distinguishes it from the set_workspace_member_role/folders/api_access siblings. An agent can pick this tool from the name plus first sentence alone.

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 concrete when-not guidance, listing three subject-level exclusions (owner, self, pending invitee) plus a permission prerequisite ("Members" right). What it doesn't do is name a sibling alternative explicitly — it never says "use remove_workspace_member to fully remove" — so the routing is implied by contrast rather than stated.

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