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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, and the description still adds real value: the default audioKbps of 192, the guaranteed Discord 20 MB answer on every call, the error behavior when neither param is set, and the decimal vs binary unit convention. Only the exact return shape is left unexplained, and an output schema exists anyway.

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?

Purpose and required durationSec come first, followed by the two modes, then units and caveat — a sensible front-loaded order with no filler. Some sentences are heavily packed (units, Discord limit, and scope crammed into consecutive clauses), which slightly hurts scanability.

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 4-parameter, single-call calculator with an output schema, this covers everything an agent needs: what is computed, how to choose the mode, defaults, unit conventions, error condition, and what it does not do. 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 coverage is 100%, so baseline is 3, but the description adds semantics the schema lacks: kbps is decimal (1000 bit/s) and MB is 1,000,000 bytes, plus the mode-selection meaning of videoKbps vs targetCapMb. The audioKbps default of 192 is repeated rather than new.

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+resource combination: arithmetic to compute video file size and bitrate for a clip of durationSec. It also explicitly bounds scope with "it does not inspect or encode files," which distinguishes it cleanly from every sibling (aspect ratio, safe area, subtitles, tempo, placement).

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 two mutually exclusive invocation modes (pass videoKbps -> file size; pass targetCapMb -> max bitrate) and names the real-world situations: "plan an export or hit an upload cap." It also states the negative case (no file inspection/encoding) and the error condition when neither mode parameter is supplied.

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