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

Annotations already flag destructiveHint and idempotentHint, but the description goes well beyond them, disclosing the concrete effects (loss of company and signature access, invitation withdrawal), irreversibility, and an authorization/confirmation requirement.

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?

Dense, front-loaded single paragraph: the destructive/irreversible warning leads, then outcome branching, then confirmation, then authorization limits. No sentence is filler.

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 2-parameter mutation tool with no output schema, the description supplies everything an agent needs: safety profile, irreversibility, effect on both member states, and caller restrictions. No meaningful gap remains.

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%, with both 'email' and 'company' fully documented (including the slug-or-id format for company). The description adds no parameter-level detail beyond that, so the baseline 3 applies.

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 destructive verb and resource ('removes a person from the company') and immediately differentiates the two outcomes: joined member vs. pending invitation. An agent can distinguish this from add_member, list_members, and update_member_field at a glance.

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?

Explicit preconditions and exclusions: 'Confirm with the user before calling', 'Company owners only', and 'Nobody can remove themselves or the primary owner.' These are exactly the conditions that determine whether the tool should be called and who may call it.

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