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

With no annotations, the description carries the full burden and does well: it discloses the destructive consequences ('sessions, project keys, invites and tool grants stop working immediately') and the authorization requirement ('Owners only'). It stops short of stating reversibility or re-addability, but the immediate-effects disclosure is substantive.

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?

Two tightly packed sentences in logical order: action → consequences → permission. Every clause earns its place; there is no filler or restatement of what the schema already documents.

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 destructive, owner-gated tool with two fully documented parameters, the description covers the core operational facts: what is removed, what stops working, and who may call it. Minor gaps are error conditions (e.g., email not found) and reversibility, which are secondary for a removal action.

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% — both email and workspace already have descriptions, so the baseline is 3. The tool description adds no parameter-level meaning beyond the schema; its permission note ('Owners only') relates to the caller, not the parameters.

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 — 'Remove a person from the workspace' — and adds distinguishing behavioral detail (sessions, project keys, invites, and tool grants stop working) that clearly separates it from sibling tools like users_add, users_invite, and users_list.

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 implies usage context — permanent removal with immediate revocation — and flags the 'Owners only' eligibility gate. However, it never explicitly names alternatives or says when not to use it, such as when only access should be revoked rather than the person removed (set_access, unshare).

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