get_anim_curve_data

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, but the description adds real behavioral detail: distinct return shapes for float vs transform curves and the important found=false-is-still-success case. This is context structured fields do not carry.

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?

Front-loaded with the verb and resource, then the curve-type behavior, then the error case, with a compact return object listing. Every sentence earns its place; the Returns line slightly overlaps the prose but aids the no-output-schema case.

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 carries the return-value burden and does so fully by enumerating the returned fields and explaining the found=false success case. Nothing essential for correct invocation 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, and the description adds meaning above that by explaining the consequence of curve_type: float yields flags/num_keys/keys as time-value pairs while transform yields only flags and a summed num_keys.

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 (read) plus a precise resource (one curve of a UAnimSequence) and further qualifies the behavior by curve type. An agent can distinguish it from curve-listing or mutation siblings, though no sibling is named explicitly.

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?

The 'without changing it' phrasing and the found=false note imply this is a safe read and how a missing curve is reported, which guides usage. However, it never says when to prefer this over get_anim_curve_names or evaluate_curve_at_time, so no explicit alternative routing is provided.

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