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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it handles this well. It explains that the monitor token is read-only, that `duration` is computed at read time over an event window, and that `p50_ms` is a low median representing a real observed duration. This goes well beyond a generic status description.

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?

The description is longer than a one-liner but every sentence contributes: scope, token semantics, schedule field, and unique duration fields. It front-loads the core purpose and keeps the most distinctive detail for the end. Some phrasing is dense, but it remains efficient for the behavioral nuance it conveys.

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?

There is no output schema and no annotations, so the description must supply key return and behavior information. It covers `next_expected_at`, `duration`, and the read-time computation, which are the most important non-obvious fields. It does not fully describe the complete response structure or explicitly clarify the `guest_token` parameter, leaving some gaps for a status tool of this complexity.

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 schema already documents `id` and `token`, but `guest_token` has no description. The text adds useful meaning around token roles ('monitor token only reads') and advises using the endpoint token, but it never explicitly connects 'monitor token' to the `guest_token` parameter. With 67% schema coverage, the description compensates only partially for the undocumented parameter.

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 'Status of one endpoint,' clearly identifying the verb-like purpose and resource. It also distinguishes itself from sibling list tools by noting that 'only this endpoint carries duration' and 'the list does not pay for it,' so an agent can confidently pick this over list_endpoints.

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?

The description gives concrete usage context: use the endpoint token if you have it, and use the monitor token when you need read-only dashboard access without exposing owner credentials. It also implies that for duration fields you must call this endpoint rather than the list, but it does not explicitly name sibling alternatives or state when *not* to use this tool.

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