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

Annotations only mark it as non-read-only, non-idempotent and open-world; the description goes well beyond by disclosing the credit cost model ('1 credit = 1 minute of processed video'), that failures are not charged, that wait=true blocks up to 50s, the 300-frame ZIP threshold, and the free-plan resolution cap.

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?

Front-loads the action and the cost caveat, then uses tight bullets for modes, defaults and workflow. Every sentence carries distinct information with no restatement of the name or 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?

For a 14-parameter async job tool with no output schema, the description covers cost, delivery format, blocking behavior, polling path, plan limits, and the platform boundary. An agent has everything needed to invoke it and interpret the immediate return.

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, but the description adds real meaning: it explains that exactly one mode applies, how mode is inferred from count/timestamps, and the defaults for format, resolution and delivery that the schema states only tersely.

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 ('Queue a frame extraction') and immediately scopes it to 'a public video URL'. It is clearly distinguishable from siblings like getvideoframes_get_job or getvideoframes_list_jobs, and the supported URL list removes ambiguity about inputs.

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 the follow-up workflow explicitly ('Returns immediately unless wait=true ... Then poll getvideoframes_get_job') and routes non-frame needs elsewhere ('If the user also wants a transcript ... connect GetTranscribe'). It does not, however, distinguish this tool from the sibling getvideoframes_render_frames or getvideoframes_create_demo, so the routing among near-neighbors is partial.

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