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

Annotations already indicate this is not a read-only or destructive operation. The description adds valuable context: it returns a handle and upload command, explains time limits (3-hour lapse, 72-hour wait for finished projects), privacy ('Nothing is public'), and that no account is needed. It doesn't discuss idempotency (calling twice) or failure outcomes, but given the annotation coverage, the description provides solid behavioral depth.

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?

The description is a single paragraph but dense and well-structured: purpose first, then steps, then time limits, then privacy. Every sentence adds necessary information without redundancy. It could benefit from bullet points for readability, but it's appropriately sized for the complexity and doesn't waste words.

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?

Given 7 parameters (all documented), no output schema, and a multi-step workflow, the description covers the essential flow: returns a handle, provides upload commands, instructs to call finish_project, and explains timeouts. It doesn't detail the upload command's format or potential errors, but the agent has enough to proceed correctly. It also references list_devices indirectly via schema defaults, which is adequate.

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 each parameter is well-documented (e.g., headline length, file_path expansion rules). The description adds extra meaning by explaining that screens are in store order and that the first screenshot 'sells the app', which is not in the schema. It also clarifies that the upload command sends screenshots to storage, linking to the file_path parameter. This goes beyond schema descriptions.

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 description clearly states the tool's function: it starts a screenshot set with 1-6 screenshots and returns a handle plus upload command. This distinguishes it from siblings like finish_project (which completes the process) and list_devices (which provides device IDs). The verb 'starts' and resource 'screenshot set' are specific and unambiguous.

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 description explicitly tells the agent to run the tool once, then call finish_project with the returned handle, and warns about the 3-hour upload window. It doesn't explicitly state when not to use this tool (e.g., if a project already exists), but the workflow is clear and alternates are implied by naming finish_project for the next step. There is no mention of alternatives like get_workflow, but the active creation role is evident.

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