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

Annotations already cover read-only safety (readOnlyHint=true), and the description adds the algorithmic context that 'similarity' means pHash distance, which is genuinely useful. It also clarifies that file_a and file_b must be separately-named uploads, a non-obvious calling trait. However, it does not disclose the output score's range, direction, or thresholds, leaving result interpretation ambiguous.

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?

A single front-loaded sentence that leads with the core purpose, then the calling detail, then a category tag — no filler. The only redundancy is restating the exact title 'Image Similarity' at the start, which is a minor deduction.

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 low-complexity, read-only tool with fully documented parameters, inputs and core behavior are adequately covered. The notable gap is the absence of an output schema combined with no description of the score's format or interpretation, which an agent needs to judge how to use the result. Adequate but not fully complete.

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%, both binary params are documented with accepted formats (JPG, PNG), so the baseline of 3 applies. The description adds only the minor clarification that the two uploads must be separately named, which is a small enhancement over 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?

States a specific verb ('Compute') and resource ('perceptual similarity score between two images'), and pins down the method (pHash distance). The pHash detail implicitly differentiates it from siblings like photo_image_diff (pixel diff) and analyze_image_quality, so an agent can tell them apart without opening any schema.

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?

No guidance on when to choose this tool over its many related siblings (photo_image_diff, analyze_image_quality, describe_image, etc.). There are no conditions, exclusions, or alternative tool names. The only operational hint — that inputs are two separately-named uploads — concerns calling convention, not tool selection.

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