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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds a genuine behavioral clarification that 'total_results' is per-page rather than catalog-wide, preventing a common misread; it stops short of describing pagination limits or tie-breaking.

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?

Two tightly packed sentences with no filler; the scoping rule and the total_results caveat are both front-loaded and each earns its place.

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 annotations covering safety and an output schema covering returns, the description only needed to clarify the ambiguous counter — which it does. It says nothing about the required context/llm_model/conversation_id protocol, but those are heavily documented in the schema itself.

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 schema already documents id provenance, page/limit bounds, locale, and the analytics/context fields, so the description's only parameter-adjacent content just restates schema facts. Baseline 3 applies.

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+resource ('find images visually similar to a given StockCake image id') and anchors the input's provenance to a sibling tool ('from search_images results'), so an agent can distinguish it from search_images without opening the 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?

The parenthetical sourcing rule ('from search_images results') tells the agent when this tool is applicable — after a search — but it does not explicitly state exclusions or contrast with other related tools like get_image.

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