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

Annotations already declare destructiveHint=true and openWorldHint=true, yet the description still adds real value by explaining what overwrite actually does: it rewrites bytes at existing paths and can break saved designs referencing those paths. That is the specific consequence an agent needs. It stops short of describing per-file failure semantics beyond 'completed and failed files'.

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 tight clauses with no filler, and the primary capability is front-loaded ahead of the transport caveat and the overwrite warning. Slightly dense and semicolon-chained, but every sentence carries distinct information.

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?

An output schema exists, so the description needn't detail return shape, and its note that results identify completed versus failed files is a helpful pointer. Combined with the destructive-warning coverage, what remains missing is only scoping semantics for the four undocumented required parameters.

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 43%, so the description must compensate, and it only partially does: it clarifies the sources array forms and the overwrite consequence. projectId, deviceType, platform, and the url/base64/filename subfields have no description in either place, and the targetPath constraint (overwrite=true, exactly one source) is covered only by 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?

States a specific verb and resource ('Uploads screenshot images to a project') and names the accepted input forms (HTTPS URLs, base64, local files on npm/stdio). It does not explicitly contrast with nearby siblings such as upload_asset, prepare_asset_upload, or replace_asset, so an agent must infer that this is the screenshot-specific path.

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 transport restriction ('local files are supported only by the npm/stdio transport') is genuinely useful conditional guidance, but the description never says when to pick this tool over upload_asset, replace_asset, or prepare_asset_upload. Overwrite behavior is explained, but the choice of folderId versus targetPath is left entirely to the schema.

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