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

Annotations already declare a non-read-only, idempotent, non-destructive write; the description reinforces this with an explicit WRITE marker and adds real behavioral context beyond the annotations: the speech refusal (unless allow_speech), the duplicate-frame limit on how low the ramp can hold (unless allow_duplicates), and the 12-span cap. It still doesn't say what happens to any prior speed effect on the same range.

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?

A single dense paragraph with zero filler, front-loaded by the two labels an agent most needs first (PROJECT-SCOPED, WRITE) before the mechanics. Every clause carries distinct operational information.

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 10-parameter write tool with no output schema, the description covers scope, operation kind, the result value (project identity), the geometry of the ramp, refusals, and the duplicate-frame edge case. Nothing essential to calling it safely 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 only 10% (project_id alone is documented), so the description must carry the load. It does define low, hold ("share spent at the low"), insert, curve-by-implication (eased), and allow_duplicates/allow_speech, but gives no interpretation of id, start, or end beyond the loose phrase "program window".

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 and the exact shape it produces: an eased slow-motion swing 1.0 -> low -> 1.0 as up to 12 contiguous speed spans, or constant-rate pieces over an insert. This clearly distinguishes it from set_speed (constant rate) and remove_speed among the many add_*/set_* siblings.

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?

It gives explicit preconditions and exclusions: the call is project-scoped, applies either to a program window inside one shot or to a whole insert via insert=id, and is refused over speech unless allow_speech. It does not explicitly name set_speed as the alternative for non-ramped speed changes, so the routing is implied rather than stated.

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