build_start

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

Annotations already flag destructiveHint=true and openWorldHint=true; the description adds genuinely non-obvious behavior: the call is asynchronous (returns a run id immediately), the host lease is server-owned and auto-released at terminal status, and lease phase equals the run `kind`. It omits any note on failure modes of the SSH command itself or permission requirements, keeping it short of a 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?

What the tool does is front-loaded in the first clause, followed by operational guidance and then lease semantics. The STUCK/list_hosts passage is dense and slightly tangential to invoking this tool, though it does explain how to interpret the resulting run's state.

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?

Output schema exists, so return values needn't be explained, and the description still states that a run id comes back immediately. Async behavior, lease lifecycle, and the correct follow-up call are all covered, which is everything an agent needs to invoke this 5-parameter, 2-required 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 coverage is 80%, so the baseline is 3, but the description adds real meaning to `kind`: its value becomes the lease phase shown on list_hosts, which is not stated in the schema. `notes` and `log_path` are left entirely to the schema, so this is additive but incomplete.

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 and resource ("Start a server-owned build run on a host") plus the mechanism (acquires lease, runs command over SSH, returns run id immediately). This clearly distinguishes it from build_status, build_wait, build_cancel, and build_list in the sibling set.

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?

Explicitly routes the agent away from sleep-polling toward build_wait(run_id) or build_status, which is the key decision an agent faces after calling this. It does not, however, contrast build_start with adjacent launchers like test_start or deploy_push, so the sibling-exclusion guidance is partial rather than complete.

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