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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description earns credit for adding context annotations cannot express: the secret is never returned, and the field-truncation behavior ('first characters') tells the agent it cannot recover a full key from this call.

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?

Three short clauses, front-loaded with the return-content list and closed by the two facts most likely to cause a wrong assumption (no secret, read-only). Nothing is padded or redundant.

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 an output schema present and zero input parameters, the remaining burden is only to set expectations about scope and sensitivity, which the description does. An agent has everything needed to call this correctly without a follow-up query.

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?

The tool takes zero parameters, so there is nothing to disambiguate and the baseline applies. The description correctly implies an unscoped account-wide listing rather than one requiring an identifier, which is the only semantic an agent could get wrong here.

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?

The description identifies the specific resource (the account's API keys) and enumerates exactly what each entry contains: name, first characters, scopes, enabled, last use, monthly ceiling. It is unambiguous about what the tool returns, though the list verb itself comes from the title rather than the text and there is no explicit differentiation from list_granted_scopes.

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?

Usage is only implied: 'Never the secret' hints that this is for inspecting key metadata rather than retrieving credentials, and 'Read-only' frames it as a safe inspection call. There is no explicit statement of when to call it or which sibling (e.g. list_granted_scopes) answers a related question instead.

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