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

With no annotations, the description carries the full burden and does so richly: it discloses automatic ducking, looping to fit, end fade-out, credit cost (1 per minute of main file), job_id polling via get_job for long jobs, and a 1-hour link expiry. These are exactly the behavioral traits an agent cannot get from structured fields.

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?

Four short sentences, purpose front-loaded, then behavior, cost, and job/expiry handling in that order. Each sentence delivers distinct, necessary information with no padding.

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 six parameters and no output schema, the description supplies everything needed to invoke and follow up correctly: cost model, async job_id path with get_job, and result-link lifetime. Nothing material is missing.

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 already 83% (a 3 baseline), but the description adds effect-level semantics not in the schema: what ducking actually does to the music while speech is present and that the track loops and fades. It does not touch music_volume_db, so it is not a full 5.

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 ('lay a music track under a video or voice recording') with the effect it produces, so the operation is unambiguous. However, it never distinguishes itself from media siblings like merge_media or process_audio, which the rubric reserves for a 5.

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?

Usage is only implied from 'under a video or voice recording'; the description gives no explicit when-to-use, when-not-to-use, or named alternative among the many media tools. Adequate but leaves routing to inference.

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