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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real value beyond them: it names the auth scope (hosted:read) and explicitly bounds the payload ('Never returns credentials, leases or private runner state'), which is useful security context. It stops short of describing response shape or any listing behavior, so 4 rather than 5.

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 tight sentences with zero filler: what it returns, how to invoke it, and what it will not return or do. The primary read purpose is front-loaded and the caveats follow in descending order of importance.

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, so the description compensates by enumerating the returned data (status, usage, expiry, public contribution links) and by stating what is deliberately withheld (credentials, leases, private runner state). Combined with the annotation-covered safety profile and the trial_id guidance, an agent has everything needed to select and call this tool correctly.

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 must carry the semantics, and it does for the one meaningful decision: omitting trial_id returns your own trial, while supplying one must be an exact ID. The UUID format/pattern itself is already in the schema, so the description correctly stays at the semantic level rather than restating types.

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 ('Read') and resource ('hosted trial status, usage, expiry and public contribution links') for the OAuth grant owner's trial, with the required scope 'hosted:read' called out. This is clearly distinguishable from action-oriented siblings like launch_hosted_agent and stop_hosted_agent without opening any 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 explicit invocation guidance ('Omit trial_id to list your own trial, or provide an exact trial ID') and an explicit when-not: 'Does not launch, resume or extend a trial.' That negative boundary routes the agent away from the lifecycle-mutation siblings, so nothing important is left to inference.

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