reverse_image_search

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds that the corpus is Shutterstock and the input is your own image, but omits that at least one of image_url/image_path must be provided despite zero required parameters, and says nothing about file constraints beyond 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?

A single front-loaded sentence with the action and target stated first, followed by concrete input examples. No filler or redundant restatement of the schema.

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?

Return values are covered by an output schema and the safety profile by annotations, so the remaining burden is small. The only real omissions are the at-least-one-image-source constraint and differentiation from find_similar.

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 coverage is 75% and the schema itself documents image_url, image_path and per_page limits, so the baseline applies. The one gap the description could have filled — what commercial vs editorial licensing means for results — is addressed nowhere, and the mutually exclusive nature of the two image inputs is left implicit.

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 names a concrete verb (find) and resource (Shutterstock images) and clarifies the query mode is 'images that look like one of your own', which separates it from keyword search. It stops short of naming the closest sibling, find_similar, which is the main ambiguity risk.

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 examples (sketch, mood board, a photo to replace) imply when this is useful, so the use case is inferable. There is no explicit guidance on when to prefer this over search_images or find_similar, and no stated prerequisite about supplying exactly one image source.

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