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

Annotations (readOnly=false, openWorld=true, idempotent=false, destructive=false) only sketch the write profile; the description adds the zero-argument upload-widget behavior, the upload_url fallback, the response shape (current with photo_id), the semantic effect of ai_generated (shown as illustrations, never as real premises), and failure handling (resolve failed uploads before photos_done). It also names the one hard prohibition: never invent a URL or send a local file path.

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?

Nearly every sentence carries procedural weight, and the audience restriction and core save/list behavior are front-loaded. It is dense to the point of overload, though: generation policy, cost disclosure, error recovery, and the photos_done gate are packed into one unbroken block, and the list-photos fallback sits mid-paragraph rather than being surfaced early.

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 five optional parameters, no output schema, and mutations involved, the description covers what is missing elsewhere: the return value (upload widget, upload_url, or the current photo list), the ownership/sign-in prerequisite, and the failure path. Nothing an agent needs to call this correctly is absent.

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; the description still adds meaning beyond the schema by constraining urls to downloadable image addresses with a never-invent rule and supported attachment links for files, and by explaining that ai_generated changes how the page presents the images. It does not address the draft_id vs business_id distinction, which is left entirely to the schema.

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?

Opens with a specific verb+resource and an audience gate ("Only for business owners signed in to Awning"), then states the dual behavior: saves photos and, when called with nothing, returns an upload widget plus the current photo list. The final sentence explicitly separates it from owner_remove_photos, so the agent can route without opening either 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?

Gives explicit when-to-use and when-not ("to take photos off use owner_remove_photos"), a preference ordering (owner's own photos of the actual place first, generated illustrations only if none or more wanted), a prerequisite flow (owner must approve each picture; explain image-tool cost first), and a completion gate (mark photos_done only after successful uploads).

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