Diff Visual Checkpoints

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds value by specifying the types of changes detected (additions, deletions, visual drift regressions), but does not mention prerequisites or output behavior.

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 sentence that front-loads the action and result, with no redundant words. It earns its place by being compact and informative.

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?

With two fully described parameters, clear annotations, and a focused purpose, the description is largely sufficient. However, it does not describe the return format or any error conditions, which would be useful given no output schema exists.

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%, and the parameter descriptions ('Base snapshot name' and 'Target snapshot name to compare against') already clarify meaning. The tool description adds no additional parameter semantics beyond the schema.

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 specific verb 'Diff' with the direct object 'two snapshots' and states the outcome ('locate additions, deletions, or visual drift regressions'), clearly distinguishing it from sibling tools like 'save_visual_snapshot' or 'get_visual_diff' by its focus on snapshot comparison and drift detection.

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 usage for comparing snapshots but does not explicitly state when to prefer this over alternatives like 'get_visual_diff' or 'compare_states'. There is no when-not guidance, so the agent must infer context from the snapshot-specific wording.

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