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

With no annotations, the description carries the full load and does it well: it discloses the ownership/auth prerequisite, that keys never expire, that secrets are never returned, and precise semantics for last_used_at (minute granularity, null plus never_used=true). What it omits is operational behavior an agent would care about — result ordering and whether the list is paginated or capped.

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?

One dense paragraph that front-loads the action and scope, then layers return fields, lifespan/security behavior, and filters in descending order of importance. Every clause carries information; there is no filler or restatement of the name.

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?

An output schema exists, so return values need not be described, yet the description still names the fields an agent should expect — helpful, not redundant. For a three-parameter owner-scoped list tool this is nearly complete; only pagination/ordering and the shop_id contract remain unaddressed.

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 0%, so the description has to compensate, and it does for two of three parameters: 'filter by audience (any or mcp)' maps to audience and 'include revoked keys' maps to include_revoked. shop_id is only implied via 'a shop's' and the meaning of the 'mcp' audience value versus 'any' (what class of key it selects) is not explained, leaving a small gap.

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 (List) and resource (a shop's named agent keys) and enumerates exactly what is returned: label, scopes, audience, creation time, last-used, revoked. The 'key itself is never returned' line separates it from any credential-retrieval sibling, and '(owner only)' scopes the audience, so an agent can place it against keys_revoke and keys_connections without opening a 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 clear context: owner-only access, and the two filter levers (audience any/mcp, include_revoked). It also implies the follow-on action ('revoke a key the shop no longer uses'), pointing toward keys_revoke, but it never names that sibling or states an explicit when-not condition, so the routing is inferential rather than spelled out.

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