editor_job_start

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

With no annotations, the description carries the full burden and discloses strong traits: asynchronous return, single-job serialization, and the specific error (job_conflict naming the running job). It also describes what 'compile' does operationally (waits until the editor reloads and settles). It does not cover failure recovery, cancellation, or permission requirements, but the key behavioral profile is present.

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?

Front-loaded with the core purpose and non-blocking semantics in the first clause, then layering kinds, conflict behavior, and follow-up. Every sentence, including the compile parenthetical, carries actionable information; nothing is redundant.

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?

An output schema exists, so return values needn't be explained, and the description still ties results to the sibling sync tools. Combined with the async/conflict/follow-up guidance, an agent has everything needed to invoke this 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 100%, so the baseline is 3, but the description genuinely adds meaning by mapping each kind value to behavior ('compile ... wait until the editor has reloaded and settled', 'open_scene (path)') and tying path to the open_scene kind. This is meaning beyond the raw enum list in the schema.

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 (Starts) and resource (a long editor operation as a job) and immediately clarifies it returns at once rather than blocking. The enumerated kinds and the note that its result matches editor_compile/editor_play_mode/editor_open_scene make it distinguishable from those synchronous siblings without opening their schemas.

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?

Clearly establishes the usage context (long operations, non-blocking return) and names the follow-up tools (job_wait, job_status) plus the one-at-a-time constraint. The alternative blocking siblings are referenced only indirectly ('its result is what editor_compile... return'), so the explicit selection rule between this and those sync tools 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.