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

Goes well beyond the annotations: straight-line constant-velocity corners are left untouched, lost frames split the track into independently smoothed parts, and the call is free. What is not disclosed is the consequence of the idempotentHint=false flag — whether re-running compounds the smoothing or whether the track is modified in place versus copied.

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 is front-loaded in the first sentence, followed by behavioural guarantees, the use/alternative rule, the return summary, the verification step and cost. Every clause carries distinct information; nothing is restated from the schema or annotations.

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?

With no output schema, the description correctly summarises the response (new quality verdict plus flagged ranges) and tells the agent how to inspect the result. The remaining gap is whether the operation mutates the existing track or produces a new version — relevant given idempotentHint=false and destructiveHint=false.

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%, and the enum descriptions already explain kalman/one-euro/savgol and the strength scale. The description's only added parameter meaning is indirect (lost frames are not moved, which touches range handling). Baseline 3 applies when the schema carries the semantics.

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 (smooth an object track's per-corner x/y over time) and enumerates the three concrete algorithms. It also names the sibling it is not (edit_track handles drift/jumps), so an agent can separate it from neighbouring track tools without opening a schema.

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?

'Use it when a pinned picture shakes on a still surface; fix a drift or a jump with edit_track first' gives both the triggering condition and an explicit routing rule to the alternative. It also prescribes a follow-up verification step (preview_range with overlays ["tracks"]).

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