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

Goes well beyond the annotations by disclosing who is refused (service account, AI agent, subworker, autonomous run) and the completeness rule that key_ids must list every key exactly once — real invocation constraints an agent cannot get from the schema. One tension worth noting: describing a full-set assignment suggests repeated identical calls produce identical state, which sits awkwardly with idempotentHint=false, though the description never explicitly claims idempotency.

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 operation and effect ('first tried first'), then prerequisite, then eligibility. The refusal enumeration is dense but every clause is operationally relevant; slight tightening of the eligibility list would help but nothing 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 single-parameter, non-destructive mutation with no output schema, the description covers the effect, ordering semantics, input completeness rule, source of ids, identity restrictions and per-context refusal cases. Nothing an agent needs to call it correctly is missing.

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 schema already states 'in the order Ankra should try them', so the baseline is 3. The description adds modest value with the 'exactly once / every key on your profile' completeness constraint, which prohibits partial lists, but repeats the ordering meaning the schema already carries.

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 ('Set the order Ankra tries your own AI keys in') and immediately disambiguates from its siblings by noting the ids come from list_personal_ai_keys, while the 'personal' scope separates it from org-level key tools. An agent can identify this as the ordering tool without opening the 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?

Gives an explicit prerequisite ('The ids come from list_personal_ai_keys') and a detailed eligibility boundary: only the person themselves, in their own chat or over MCP with their own token, refused for service accounts, AI agents, subworkers and dispatched/autonomous runs. It does not explicitly contrast against rename_personal_ai_key, test_personal_ai_key or delete_personal_ai_key, so when-to-use versus those siblings is left implicit.

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