evaluate_visual_patch

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

Annotations declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the description is not contradictory. However, it adds almost no behavioral context: it does not disclose whether the tool writes to output_dir, executes operations, or mutates state, leaving the agent to infer side effects from the schema.

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 short, but this is under-specification rather than effective conciseness. The single sentence does not convey the tool's function or parameter meaning, so it fails to earn its place as a usable definition.

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?

Given a 9-parameter schema, no parameter descriptions, a rich sibling set, and no output-format explanation, this description is far too incomplete. Even though an output schema exists, the tool's core behavior and required parameters remain opaque.

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 explains none of the 9 parameters. Terms like 'operations', 'data_bindings', 'visual_criteria', and 'max_operations' are completely undocumented, so an agent cannot know how to set them correctly.

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 reads as an instruction about response style ('Compare compact evidence') rather than a clear statement of what the tool does. It never names the resource being evaluated or mentions a visual patch, and it does not help distinguish this tool from siblings such as render_spec or apply_patch.

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 call this tool versus any of the 12 siblings. The only clause, 'include full specs/manifests only on request,' addresses output verbosity, not tool selection or invocation context.

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