get_recipe_img

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

With no annotations, the description carries the full load. It discloses that the call returns a static image and behaves differently in production (proxied), which is real behavioral context, but it never states auth requirements, error behavior for missing files, or content type.

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 useful content is two short clauses; the rest is a title restatement and a 20-item keyword dump that adds noise without information. Structure is a raw dump rather than front-loaded guidance.

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?

No output schema and no annotations means the description should cover returns, auth, and both parameters. It covers roughly one parameter and the production-proxy caveat, leaving the file_name enum semantics and access requirements unexplained for a 2-parameter asset fetcher.

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%, so the description must compensate. It explains only recipe_id ('takes in a recipe id') and says nothing about file_name or the three-value ImageType enum (original/min-original/tiny-original), leaving the second required parameter semantically opaque.

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 and resource ('Get image' for a recipe), and the route notation clarifies it retrieves a static asset by recipe_id and file_name. It is distinguishable from mutation siblings like update_recipe_image and delete_recipe_image, though it never names the closest read sibling get_recipe_asset.

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 note that the route is proxied in the docker image and 'should not hit the API in production' is genuinely useful context, but it is operational trivia rather than a when-to-use statement. No guidance is given on choosing this over get_recipe_asset or get_user_image.

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