Generate Media

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

With no annotations, the description carries the behavioral burden and does it well: it discloses that the call returns before the job is done, enumerates terminal states, and explains default routing behavior. This goes well beyond the schema, though it does not mention cancellation or lifecycle side effects.

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 sentences, all high-signal. The most important action is front-loaded, the async behavior comes immediately after, and the backend guidance is a compact decision rule. No 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?

The description is complete on the job lifecycle and backend routing, and an output schema exists for the job-handle return. It is less complete for a 7-parameter tool because it never explains modality-specific parameter applicability (e.g., duration_s vs width/height) or require_tags, and does not point to list_capabilities for discovery.

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 description coverage is 0%, so the description must explain the parameters, but it only adds semantics for backend. prompt, modality, width, height, duration_s, and require_tags are left to their types/names, and require_tags in particular has no hint of its meaning or effect.

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?

Description opens with a concrete verb and resource: 'Start a generation and return a job handle.' This clearly separates it from siblings like get_job, cancel_job, and list_jobs, all of which are later referenced or implied by the async lifecycle.

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 makes the async workflow explicit: call this to start the job, then poll get_job with the returned job_id. It also gives concrete guidance on when to set backend vs leave it unset. It does not, however, spell out when to prefer list_capabilities first or when not to call this tool.

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