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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds genuinely non-obvious context: the removal is immediate, team briefs are preserved, the last-admin case is blocked, and external recipient/billing state is untouched. That blast-radius description is exactly what a destructive tool needs and goes beyond the annotation flags, though it does not address reversibility/re-invitation.

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?

Four short clauses, with the hard constraint ('Admin only') front-loaded and no redundant restatement of the tool name or title. Every sentence carries a distinct fact.

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-required-param destructive tool with no output schema, the description supplies the constraints and effect scope an agent needs, and annotations cover the safety profile. The one real gap is parameter identification, which the schema only partly documents.

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 only 33% — user_id and workspace_id carry no descriptions, and confirm's description is in the schema rather than the description text. The description contributes no parameter-level meaning (no format, no identification of what user_id/workspace_id must reference), so it fails to compensate for the coverage 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?

States a specific verb and resource ('remove this person's internal team access') and scope-limits itself against adjacent operations by noting what it does not touch (external recipient permissions, billing responsibility). It does not name siblings such as update_workspace_member_role or leave_workspace, so the agent must still infer the boundary, but the resource is 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?

Gives a clear precondition ('Admin only') and an explicit prohibition ('Cannot remove the last admin'), which is real when-to-use guidance for a destructive call. It does not route the agent to alternatives (e.g. leave_workspace for self-removal, update_workspace_member_role for role changes), so it stops just short of a 5.

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