evaluate_at_time

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered, and the description correctly reinforces that this is a computation rather than a mutation. It adds no further behavioral context, however: nothing about what happens when the target path does not exist, whether values are interpolated between keyframes, or what the response looks like.

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?

Three short sentences with the core operation front-loaded, the optional filter second, and the use case last. No filler, though the final "Use to VERIFY an animation" sentence is thinner than the guidance a verifier workflow usually needs.

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?

There is no output schema, so the description is the only place a caller could learn the shape of the returned values, and it does not say whether results come back as a flat path-to-value map or something else. Combined with the unexplained session/request/revision parameters, the definition is adequate but leaves meaningful gaps for a five-parameter tool.

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 40%, so the description carries real weight here: it explains the units of `timeMs` and clarifies that `target` is an optional single-track filter, complete with a concrete example path. It says nothing about `requestId`, `sessionId`, or `expectedRevision`, leaving three of five parameters entirely undocumented in both schema and description.

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?

The description gives a specific verb and resource: "Compute animated property values at a given time (ms)", which tells an agent exactly what the tool produces. It does not, however, differentiate itself from the sibling `evaluate_frame`, which by name appears to do something very similar, leaving ambiguity between the two.

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 to VERIFY an animation" gives a stated intent, which is more than nothing, but it provides no when-not conditions and never names an alternative such as `evaluate_frame`, `get_scene`, or `describe_timeline`. The agent must infer the boundary between this and the other read/evaluate tools.

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