find_similar

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and external reach are covered. The description adds only that matching is by visual appearance ('look like') rather than metadata, and says nothing about pagination behavior, result limits, or how similarity is scoped across asset types.

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 no wasted clauses. It is appropriately tight, though the brevity comes at the cost of the missing guidance noted in other dimensions.

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?

An output schema and annotations reduce the burden, but a read tool with an enum param and a direct sibling overlap (reverse_image_search) needs more than one sentence. Nothing clarifies what kind of results come back or how this differs from the other similarity/search siblings.

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%, with only asset_type lacking a schema description. The description adds no meaning to id, page, per_page, or asset_type beyond the schema text; 'one you already have' only loosely restates that id refers to an existing asset.

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 states a specific verb and resource: find images or videos visually similar to an existing Shutterstock asset. That is clearly distinct from search_images/search_videos (keyword search), but it does not distinguish itself from the sibling reverse_image_search, which appears to cover overlapping intent.

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?

Usage is only implied by the phrase 'one you already have from Shutterstock,' suggesting the tool requires an existing Shutterstock asset id. There is no explicit when-to-use/when-not guidance and no routing to alternatives such as reverse_image_search or search_images.

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