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

Annotations establish a non-read-only, non-idempotent, non-destructive write, and the description adds substantial context beyond them: that a changed definition or size becomes a new version built immediately, that the response carries that build, and that refusals identify the offending line or size bound. It does not disclose permission/auth requirements or what happens to prior versions on update.

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?

Four dense sentences, all front-loaded: the create/update distinction comes first, followed by definition constraints, versioning behavior, and error semantics. No filler and every sentence carries information an agent needs.

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?

For a parameterless-required, five-param mutation tool with no output schema, the description covers create vs update, definition constraints, version/build behavior, and error reporting, and even notes the response carries the build. It omits the shape of the returned build object and whether non-dockerfile fields (name, size) are partial updates, leaving minor gaps.

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 100%, so the schema already documents all five parameters (name, size, starterId, dockerfile, templateId). The description reinforces the create-vs-update role of templateId and the Dockerfile rules, but adds little syntax or format detail the schema lacks; baseline 3 is appropriate.

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 and resource ('Create a sandbox ... or change one') and immediately disambiguates the two modes via the templateId condition. It is clearly distinguishable from siblings like build_sandbox_template, delete_sandbox_template, and save_sandbox_registry without opening any schema.

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?

It explicitly states the discriminator between create and update ('omit templateId'), which is real when-to-use guidance. It does not name alternative tools (e.g., build_sandbox_template or list_sandbox_starters) for related workflows, so it stops short of full routing guidance.

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