create_build

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

Annotations already indicate readOnlyHint=false and destructiveHint=false, so the mutation profile is partially available. The description adds useful behavioral context by saying the result is a 'published' and 'durable build job', which signals that the action has a persistent, non-transient effect. However, it does not disclose whether the build process is asynchronous, whether it can overwrite existing builds, or what side effects publishing may have.

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 two short sentences with no filler or repetition. It front-loads the core action and then states the return value, which is an efficient structure for an AI agent scanning tool definitions.

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 12 parameters, no output schema, and minimal annotation detail, this description is insufficient. It tells the agent what the tool does and that it returns a durable job, but it does not clarify how to configure a successful build, what the required name represents, how primarySceneId is used, or how the returned job can be tracked. The description leaves too much to inference for a complex build-creation operation.

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 only 25% with 12 parameters, so the description must compensate. It does not explain the required name parameter, primarySceneId, minify, version, or any other build configuration field. The only parameter hint, 'for scenes', merely mirrors the existing sceneIds schema description and adds no new meaning.

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 a specific verb ('Create'), a clear resource ('published PlayCanvas build'), and the target scope ('for scenes in the designated project'). It is easily distinguishable from siblings like list_builds, get_build, and delete_build because it names the creation action and the build artifact.

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 implies this tool is used to create builds, but it provides no explicit guidance on when to use it versus alternatives like set_primary_build, download_build, or delete_build. It does not mention any prerequisite, such as having scenes ready or needing a specific project context, nor does it state when a build should not be created.

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