Product Images Create

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

The description adds substantial context beyond the annotations: accepted MIME types (jpg/png/gif/webp), a hard per-product limit of 250 images, the required write_products scope, the underlying endpoint, and the pinned API version. What is missing is failure behavior — no statement of what happens when the 250 cap is exceeded, when the URL is unreachable, or whether a successful call appends to the end of the gallery.

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?

Four tightly packed lines with the operation first and constraints after; the image formats and 250 cap sit exactly where a caller needs them. The HTTP endpoint line is somewhat boilerplate for an MCP caller, but the scope and API version lines carry real operational value.

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?

For a single-purpose mutation with full schema coverage, no output schema, and annotations already declaring it non-destructive and non-idempotent, the description supplies everything an agent needs to call it correctly: two input modes, format allowlist, per-product ceiling, and required scope. Return-value documentation is not needed since no output schema exists and nothing downstream depends on it.

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 100%, so the baseline is 3, but the description adds genuine semantic value the schema does not encode: src and attachment+filename are alternative input modes, and filename is only meaningful in the Base64 path. The pairing relationship is the key decision an agent must make and the schema leaves it implicit. alt, position, and additional_fields are left entirely to their schema docs.

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 opening sentence names a specific verb (add) and resource (image) and states the two supported input modes: public URL via src, or Base64 via attachment plus filename. It is unambiguous what the tool does, but it never names the sibling tiendanube_product_images_upload_unattached, so an agent must infer the boundary between attaching an image to a product and uploading an unattached one.

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: the presence of product_id and a per-product cap of 250 images makes it clear this is the attach-to-existing-product path. There is no explicit when-to-use versus tiendanube_product_images_update vs tiendanube_product_images_upload_unattached, and no stated prerequisite such as the product needing to exist.

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