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

Adds substantial behavior beyond the annotations: the first call is a dry-run that returns each step's cost, the total and a confirmationCode, the card shows one button, the second call starts only steps whose photo is ready, and dependent steps require re-calling with the same code once the earlier result completes. It also points to get_job for polling. This is exactly the rich context annotations alone cannot convey.

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 core purpose is front-loaded in the first sentence, followed by the two-phase protocol. Sentences are long and clause-heavy (em-dash lists, nested conditions), which makes it dense, but nearly every clause carries required protocol information so little is wasted.

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?

Despite an output schema existing, the description still explains what each phase returns (costs, total, confirmationCode, jobs), how dependent steps sequence, and the photo-vs-video scope. For a stateful two-call batch planner this covers everything an agent needs to invoke it correctly.

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, and the description earns above it by giving operational meaning to confirmationCode (gates the run, reused to trigger dependent steps) and to the steps array as an ordered plan. The dry-run-then-confirm semantics of confirmationCode are the added value the schema alone does not spell out.

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?

Names a specific verb+resource (plan photo edits across several listing photos) and states the key differentiator: one plan with one total and one confirmation rather than a confirm per photo. It also draws a clean boundary against video tools, so an agent can distinguish it from the single-step siblings like straighten_photo or enhance_photo.

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 call-timing rules: the first call runs nothing and returns costs plus a confirmationCode, and the second call (only confirmationCode) starts the steps. It also states the photos-only restriction. It stops short of naming the single-edit siblings as the alternative path, so the routing guidance is clear but not fully explicit about when to prefer them.

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