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

With no annotations provided, the description carries the full burden, and it does most of it: it states default model/resolution/duration/audio, cost multipliers for audio and resolution, a concrete billing rate for motion control (~11 coins/s, min 3s), the required parameter pairing for kling_2_6_motion, reference-count limits per model, and the async contract (returns job_id, poll check_job until status=done). It omits auth requirements, failure/retry behavior, and quota limits, so it falls short of a 5.

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 default configuration is front-loaded, which is the right priority, and most sentences carry actionable content (costs, required pairs, polling). It is dense and long, with a few parenthetical asides that could be trimmed, but little is pure 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 9-parameter async generation tool with no annotations and no output schema, the description covers the essentials an agent needs: defaults for unspecified inputs, the clarifying-question protocol, model-specific parameter requirements, cost signals, and the return/polling contract. It stops short of error handling, authorization, and output shape beyond job_id, so a 5 is not warranted.

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 only 56%, so the description must compensate, and it does add real meaning: it names the default model, explains that duration options are 4/8/12s, that aspect ratio maps to vertical/horizontal/square, that audio roughly doubles cost, and that resolution tiers scale cost to 1080p at ~5x. It does not explain the remaining enum members (grok_*, veo_3, kling_2_6) or the full duration enum, leaving some gaps against the 56% coverage.

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?

Opens with a specific verb+resource ("Generate a video") and immediately scopes it with defaults and model family. It clearly separates this from generate_image and check_job, the latter named explicitly as the follow-up poll tool. An agent knows exactly what this tool produces.

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 when-to-do-what rules: ask for the four unspecified options before calling, skip the questions if the user already supplied them or asked for "the cheapest", and use kling_2_6_motion only under a specific stated condition. Alternatives and their trigger conditions are spelled out rather than implied.

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