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

Annotations only declare destructiveHint=true; the description adds the consequences that matter: no undo, immediate loss of sign-in, retained orders/sales so reports still work, and a server-enforced block on removing the account the agent key belongs to. These are exactly the behavioral traits 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?

Purpose is front-loaded and every sentence carries information (routing triggers, precondition, edge case, side effects, server constraint). It is on the long side and the colloquial example list is slightly padded, but there is no 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?

With no output schema, the description still covers what an agent needs to call safely: the id source, the confirmation requirement, name-collision handling, irreversible effects, and the self-removal guard. Nothing material is left unspecified for a high-risk mutation tool.

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's description already says 'User id from get_team — not a name'. The description largely repeats that ('Takes the userId from get_team ONLY, never a name'), adding emphasis rather than new semantics, so the baseline 3 for a fully documented schema is appropriate.

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 someone from the merchant's team) and grounds it in colloquial routing cues an agent can match ('she left', 'take the leaver off'). It also distinguishes itself from the read path by naming get_team as the source of the userId, so the agent can tell it apart from siblings like hub_update_user or hub_delete_customer.

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 when-to-use is given via the 'she left' triggers, plus a hard precondition (CONFIRM WITH THE MERCHANT BEFORE CALLING, naming the person) and a disambiguation rule for duplicate names (list them and ask which). The source of the required id is pinned to get_team ONLY, leaving little to inference.

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