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

Annotations only give readOnly=false, destructive=false, openWorld=false; the description adds the real behavior: a two-phase upload protocol, a link-return mode, `failed` results that can be retried, hash-based deduplication so a stored file is not stored twice, and the explicit prohibition on base64 image data. It also discloses what the reply yields (image key for create_layers, asset_id for batch rows).

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?

Dense but front-loaded: the core purpose comes first, then the branch behaviors and the recording step. It is a single long semicolon-chained paragraph, which makes the multi-step protocol harder to scan than a short bulleted flow, but no sentence is purely filler.

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 3-param, zero-required mutation tool with no output schema, the description covers input modes, the required follow-up call, retry semantics, deduplication, the returned keys, and the hard 'no base64' constraint. Nothing an agent needs to invoke it correctly is missing.

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 goes beyond it by explaining the multi-step contract per parameter — each file needs SHA-256, content type and size, bytes go to its `upload_url` with that Content-Type, and `done` records each hash plus file name. `collection` is noted as being created when it does not exist. It does not spell out the per-file `name` field semantics beyond 'file name'.

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: bringing the user's own images into the workspace, with formats (PNG/JPEG/WebP) and size limit (5 MB) up front. It explicitly separates itself from find_images and from placing web-hosted images by URL, so an agent can distinguish it from siblings.

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 branches: no `files` when the user should drop images in the browser, `files` when the agent has files on disk, `done` after PUTting bytes. It also names alternatives — find_images for existing workspace images and direct https URLs for web images.

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