update_model

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

With no annotations, the description carries the behavioral burden well: it discloses that the model is rebuilt as a side effect, that each change is reported as before to after, and that an invalid change leaves the model untouched (atomicity). It omits permissions/ownership requirements and what happens when a rebuild fails after a valid patch.

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 short sentences with zero filler, front-loaded with the verb and side effect, then the parameter semantics, then the outcome guarantee. Every clause 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 mutation tool with no annotations and an output schema (so return values need no explanation), the description covers side effects, patch syntax, and failure behavior. The main remaining gap is the absence of any mention of preconditions, such as permissions or whether concurrent rebuilds are safe.

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 0% and `changes` is an untyped free-form object, so the description must compensate – and it does, enumerating the merge-patch semantics plus the z_multiply, crop_percent, drop_feature, and revert_to shortcuts. The `name` parameter is left entirely unexplained, though its meaning is fairly evident from context.

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 and resource plus an important side effect: 'Change a model and rebuild it.' This clearly separates it from create_model, describe_model, and get_spec. It never explicitly names a sibling, but the operation is unambiguous.

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?

Usage is implied rather than stated: you use this to modify an existing model, contrasted implicitly with create_model. The description does route the agent toward `revert_to` for reversing to an earlier version, but it gives no explicit when-not conditions or named alternatives.

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