elements_transform

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

Annotations already include destructiveHint: true, so the agent knows this is a write operation. The description adds the useful detail that the transform is 'appended' (implying it adds to existing transforms rather than replacing), and limits input to 'allowlisted numeric' structured objects. However, it does not disclose side effects, reversibility, or any state changes beyond appending, so the burden on the description is only partially met. The description is consistent with the annotations.

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 a single, efficient sentence that front-loads the key action ('Appends an allowlisted numeric SVG transform') and ends with an important constraint. Every word contributes to understanding the tool's core purpose, with no filler or redundancy. This is a model of conciseness.

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?

The tool has 5 required parameters, a complex transform schema, and a destructiveHint annotation, yet the description covers none of these details. It does not explain the purpose of expectedRevision (optimistic concurrency), workspaceId, ids, or path. Given that an output schema exists, return values are covered, but the description leaves the agent without guidance on parameter semantics, how the transform is applied, or what 'selected elements' means in the context of the other parameters. This is notably incomplete for a tool of this complexity.

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%, so the description must compensate by explaining parameter meaning. It does not. The description only refers to the transform concept but never clarifies what each parameter (ids, path, workspaceId, expectedRevision) represents or how they relate. The transform schema is complex (oneOf with many kinds), but the description adds nothing beyond it. With no parameter explanations, agents must rely solely on the schema, which is insufficient given the tool's complexity.

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 uses a specific verb ('Appends') with a clear resource ('SVG transform to selected elements') and adds a critical qualifier ('allowlisted numeric' and 'without accepting transform strings'). This precisely distinguishes it from sibling tools like elements_update (which presumably updates other properties) and elements_arrange (ordering). The phrase 'selected elements' and 'append' clearly convey the action and scope.

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?

There is no guidance on when to use this tool versus alternatives. The description does not mention any sibling tools, exclusions, or context such as 'use this instead of elements_update when applying transforms.' The implied usage (for applying transforms) is present, but no explicit conditions or alternatives are provided, leaving the agent to infer routing on its own.

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