Upload a screenshot

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

Beyond the annotations (readOnly=false, destructive=false, idempotent=false, openWorld=false), the description discloses the size/format pre-validation ('anything else is refused before upload'), cost (free, no credits), a side effect the annotations miss (counts against the account upload quota), and retention (deleted after 30 days). The one gap is non-idempotency: annotations say idempotentHint=false but the description never says repeated uploads of the same file create distinct uploadIds.

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 short labeled chunks — what it does, when to use it, cost/lifecycle — with the verb and the return value front-loaded. No sentence is filler, and the parenthetical about siblings is load-bearing routing 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?

For a one-parameter upload tool with an output schema, everything an agent needs to call it correctly is present: format, size cap, pre-upload validation, credit cost, quota impact, and 30-day retention of the resulting artifact. The return shape is covered by the output schema.

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% and there is a single required path parameter, so the baseline is 3; the description earns above baseline by adding the 20 MiB limit, which the schema's maxLength:4096 does not cover, and by restating the accepted formats at the point of use. It stops short of saying the path must be absolute and locally readable by the server, which the schema does state.

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 one raw app screenshot from a local file'), plus concrete accepted formats and a 20 MiB cap, and names the return value (uploadId). An agent can distinguish this from generate_screenshot and create_screenshot_set without opening any 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?

'When to use: once per raw screenshot before create_screenshot_set or generate_screenshot' names both the ordering and the alternatives, and explicitly notes those siblings also accept { path } and upload for you — meaning this tool is often unnecessary. That is when-to-use and when-not-to-use in two sentences.

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