start_host_run

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

Annotations are all false: readOnlyHint=false correctly signals this is a mutation, destructiveHint=false signals it's not destructive. The description says 'start' which aligns with the mutation annotations. It adds the behavior of returning the first stage, which is useful context beyond the annotations. However, it doesn't disclose side effects, state transitions, or failure/rejection behavior for a state-changing operation, which would be valuable given the lifecyle context of sibling tools.

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 concise sentence that is front-loaded and to the point. No filler or redundancy. It fits the 'two-sentence or less' ideal for conciseness, though it could be improved by adding a second sentence with usage guidance without becoming bloated.

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?

This is a state-changing operation on a durable resource within a complex lifecycle of many sibling tools, and the description is extremely thin. An output schema exists (mitigating return-value explanation needs), but the description doesn't explain the state transition, the meaning of 'prepared', the revision check semantics, or failure behavior. Given the complexity of the surrounding tool ecosystem, a single sentence is insufficient.

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% and there are 2 required parameters (run_id, expected_revision). The description does not explain what these parameters mean beyond their names, which are somewhat self-explanatory. However, 'expected_revision' is notably cryptic — an agent would not know what revision is being expected, what value format to use, or why it's required. The description should at minimum clarify the semantics of expected_revision, but zero parameter information is provided.

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 states it starts a prepared durable host run and returns its first stage. The verb 'start' plus 'prepared durable host run' is reasonably specific, but it doesn't distinguish from siblings like resume_host_run, pause_host_run, or run_fixture which may have overlapping semantics. The return behavior (first stage) is a useful detail but the overall purpose isn't sharply differentiated from the large cluster of similar run-lifecycle tools.

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 word 'prepared' implies a prerequisite (that prepare_host_run must be called first), but this is not made explicit. There is no guidance about when to use this vs resume_host_run, run_fixture, or create_host_run, nor any statement about when not to use it. The description relies on the tool name and single word 'prepared' to convey the prerequisite.

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