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

Annotations only declare that this writes and is neither idempotent nor destructive. The description adds the critical operational trait that the credential is returned exactly once and cannot be read back, plus who must receive it. That is exactly the kind of context a schema cannot convey and it prevents an irreversible misstep.

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 sentences, no filler, and the one-time credential caveat is front-loaded in sentence two where an agent will actually act on it. The middle clause 'for a runtime the withhuman CLI does not install (a service of yours speaking the Agent Approval Protocol)' is slightly dense but still earns its place as the scoping condition.

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?

No output schema exists, and the description compensates by stating precisely what the response contains (the credential, once). It leaves unstated what happens on a repeated call for the same instance and how the credential is later revoked, both relevant given revoke_agent_credential sits among the siblings.

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 every parameter (name, metadata, agent_slug) is documented inline, so the schema carries the semantics. The description reinforces agent_slug only indirectly via the 'service agent' wording and adds no new meaning about metadata or naming rules. Baseline 3 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?

The description opens with a precise verb+resource pair: 'Register an instance of a service agent and mint its credential.' It also scopes the operation to runtimes the CLI doesn't install, which separates it from create_agent and update_agent_instance without the agent needing to inspect schemas.

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?

It names both the target case (a runtime you operate yourself that speaks the Agent Approval Protocol) and the exclusion ('Personal agents' instances belong to the member who enrolls them through the CLI'). The agent knows immediately when this route applies and when to steer elsewhere.

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