elements_update

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

The annotation already provides destructiveHint=true, so the description does not need to restate that it is destructive. The description adds a behavior trait by mentioning 'typed allowlisted patches', which indicates that only certain fields are modifiable. However, it does not disclose the optimistic concurrency behavior via expectedRevision, failure modes, or the fact that it is a batch operation. The added value beyond the annotation is modest.

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, short sentence that immediately states the action and scope. It is front-loaded with the verb 'Updates' and avoids fluff. While it could include more detail, it is concise and efficient given its brevity.

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 destructive update tool with optimistic concurrency (required expectedRevision), batch execution (elements array up to 100 items), and an output schema, the description is sparse. It does not explain the concurrency mechanism, the meaning of workspaceId/path, or the effect of conflicting revisions. It also does not clarify limits like the 100-element maximum. The description leaves multiple operational details unaddressed that are essential for an agent to call the tool correctly.

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 description does not explain any of the four required parameters. It vaguely alludes to the elements array by listing 'geometry, basic styles, text, or layer labels', but it does not explain 'path', 'workspaceId', or 'expectedRevision'. The description adds minimal meaning over the schema, which itself lacks descriptions for the parameters, leaving the agent without crucial semantic context for the concurrency token and workspace/document identification.

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 the verb 'Updates' with a concrete resource: 'bounded SVG geometry, basic styles, text, or layer labels' and mentions 'typed allowlisted patches', which clearly conveys a patch-based update mechanism. It is not a tautology and distinguishes itself from create/delete tools, though it does not explicitly differentiate from elements_transform or elements_arrange which also modify elements.

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 phrase 'bounded' and 'allowlisted patches' implies that only a restricted set of properties can be updated, but it does not explicitly state when to use this tool versus alternatives like elements_transform or elements_arrange. There is no mention of exclusions or when-not-to-use conditions; the guidance is implicit rather than explicit.

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