studio_execute_action

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

With no annotations, the description does substantial work: it discloses the serialization/concurrency constraint, the mandatory revision check, workspace-relative path resolution, the opt-in gate for scripts, the extra integrity requirement (expected_source_sha256) for Blender run_script with input_blend, and the narrow meaning of the returned status. It still omits side effects, reversibility, and failure modes for the mutating actions.

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?

Roughly five short sentences, front-loaded with the core operation and followed by preconditions in decreasing generality. No filler; the only weakness is that the line-wrapped fragment structure makes the precondition list slightly harder to scan than a single ordered sentence would.

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 described, and the status caveat is a nice addition. But for a tool multiplexing ten distinct actions with an untyped parameters object, the description leaves too much unspecified: no action-by-action parameter contract and no preconditions or side effects for the destructive actions. Adequate as a policy statement, incomplete as an invocation guide.

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 the parameters field is free-form with additionalProperties, so the description must carry the load — yet it only explains workspace-relative paths and names two keys (input_blend, expected_source_sha256) for one action. The per-action shape of 'parameters' for the other nine enum values, and the semantics of job_id and expected_revision, are left unaddressed.

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 concrete verb and resource: execute one serialized native action and validate output evidence. The 'serialized' qualifier differentiates it from the planning/inspection siblings, which don't run actions. It stops short of naming or contrasting siblings explicitly, and never enumerates what the ten actions mean.

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?

Several preconditions are implied ('Revision is required', scripts need server-side opt-in), and 'Return status describes this action, not completion of every project goal' is a useful interpretive rule for an agent reading results. But there is no statement of when to pick this over the other studio_* tools, no per-action eligibility rules, and no when-not-to-use guidance.

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