Run Validation

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

With no annotations provided, the description carries the burden and does disclose the key durable execution behavior: long commands in auto mode return immediately with a run id and continue in the background. However, it does not fully disclose what happens to short commands in auto mode beyond 'return synchronously' (e.g., returned data shape), or differences in async vs sync modes more granularly. The execution_mode parameter also explains some of this directly, reducing the credit.

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 three tight sentences with zero wasted words. It front-loads the core purpose, then explains the durable behavior in the second sentence, and closes with the synchronous short-command behavior. Every sentence earns its place.

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?

Given the high parameter count (13) and moderate schema coverage (54%), the description addresses the most operationally important behavioral distinction (durable vs synchronous execution) and names the follow-up tools. An output schema exists, so return-value documentation is the structured field's responsibility. However, given 13 parameters and many undocumented ones, slightly more detail on output structure when synchronous vs run-id-only would strengthen completeness.

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 54%, meaning roughly half the parameters lack descriptions (cwd, run_id, commands, tail_lines, timeout_ms have no descriptions). The description adds meaning about execution_mode and output_mode behavior but does not address the undocumented parameters like commands (which is central), tail_lines, or timeout_ms. With partial coverage, the description compensates only marginally for the undocumented params.

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 uses a specific verb+resource ('Run project checks') and clearly states the tool runs builds and test suites. It distinguishes itself from sibling run_acceptance by focusing on general project validation/checks rather than acceptance tests, and mentions the durable handling for long builds.

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 explicitly discusses execution modes and when each applies: auto returns immediately with a run id for long commands, short checks return synchronously. It names the companion tools (run_task_status, read_run_task_result) for retrieving final results, providing concrete when-to-use guidance and alternatives for follow-up.

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