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

The annotations already declare destructiveHint=true, so the description's job is to add what the flag cannot express, and it does: the key's stored copy is deleted, Ankra stops using it immediately, and the action is not recoverable — reusing the key requires adding it again. It further discloses hard eligibility refusals (service account, AI agent, subworker, dispatched/autonomous run) that determine whether the call will succeed at all.

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?

Front-loaded with the action, then the consequence, then the eligibility constraints — a sensible ordering with little filler. The final sentence packs four refusal cases into one clause, which is dense but justified by how much it matters to a caller.

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 single-parameter destructive tool with no output schema, everything an agent needs is present: what is deleted, that it is irreversible, how to source the key_id, and who is permitted to call it. Annotations cover the safety profile and the description covers the remaining risk and permission surface.

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% and the single parameter is already documented as coming from list_personal_ai_keys. The description repeats that same provenance point without adding format, validation or edge-case detail, so it neither helps nor hurts beyond the schema — 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 verb ('Remove') and a precisely scoped resource ('one of your own AI keys from your profile'), plus the secondary effect of deleting the stored copy. That is enough to distinguish it from rename_personal_ai_keys, reorder_personal_ai_keys and request_personal_ai_key without opening any schema.

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?

Explains the operating context clearly: it acts only on the caller's own key, in their own chat or over MCP with their own token, and is refused for service accounts, agents, subworkers and dispatched/autonomous runs. It also routes to list_personal_ai_keys for obtaining key_id. It stops short of explicitly naming sibling alternatives (rename vs. delete), which keeps it out of the top band.

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