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

The description explains that the tool verifies storage, records the object, and returns a media id plus public URL. This goes beyond the annotations, which only indicate readOnly=false/destructive=false. It does not describe failure handling or idempotency, but the key behavioral steps are disclosed.

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?

Three sentences, all front-loaded: the very first clause identifies the step and prerequisite. Every sentence adds a distinct, necessary piece of information: when to call, what it does, and what to do with the result. There is no filler or redundancy.

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?

Given that an output schema exists, the description need not list return fields. It covers the workflow position, prerequisite, effect, and downstream integration. It could optionally mention failure behavior or idempotency, but for invoking this step correctly, the description is 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%, and each parameter is already described (key, filename, mimeType). The description adds the workflow context that these values must match the prepare step, but it largely repeats what the schema descriptions already say. Baseline 3 is appropriate.

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 opens with a specific verb and resource: 'Step 2 of 2 for adding an image' and states it 'verifies the uploaded object, records it in the team media library and returns a media id + public URL.' It clearly distinguishes itself from prepare_image_upload by explicitly naming it as the preceding step and from update_form as a later consumer of its media id.

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?

It gives the exact timing ('call this AFTER you have PUT the file to the uploadUrl returned by prepare_image_upload'), the alternative usage ('to use the image as a quiz cover or landing-page cover, call update_form with flagImg or landingImage'), and the sequencing. No ambiguity remains about when to invoke this tool versus its siblings.

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