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

Goes well beyond the destructiveHint=true annotation by itemizing exactly what is destroyed (role, role assignments, cluster access in this organisation), what survives (account, other organisations), and the cost of reversal (a new invitation is required). It also discloses two server-side refusal rules and a confirmation requirement, which the annotations cannot express.

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?

Five tight clauses with zero filler: identity and scope first, then permission, then consequences, then refusal rules, then the confirmation instruction. The CLI twin reference is a compact recognition aid for operators and costs a single parenthetical.

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 one-parameter, non-idempotent destructive tool with no output schema, the description covers everything an agent needs: authorisation, id provenance, blast radius, irreversibility, failure modes, and a mandatory confirmation step.

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% and the single param already documents that user_id is the id shown by list_organisation_members, so the description's note about provenance repeats the schema rather than adding syntax or edge-case meaning. Baseline 3 for a fully documented single-parameter schema.

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 with explicit scope: 'Remove a member from this organisation'. This is unambiguous against siblings such as invite_organisation_member, update_organisation_member_role and list_organisation_members, which handle adjacent but distinct operations.

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 strong preconditions (needs members.manage), tells the agent where to get user_id (list_organisation_members), and states refusal conditions (a member stronger than you, the last owner) plus a confirmation rule. The only gap is that it never explicitly names update_organisation_member_role as the alternative when the intent is a role change rather than removal.

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