ae_set_comp

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

With no annotations, the description carries the full burden, and it does disclose two real traits: 'One undo step' (undoability) and the viewer side effect of open: true. However, for a 13-parameter mutation tool it never says whether omitted fields are left untouched (partial vs. full replace), which is the single most consequential behavior an agent needs.

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, front-loaded sentence that leads with the verb and resource, then enumerates targets with semicolons for easy scanning. Dense but every clause maps to a real parameter; no filler.

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 mutation tool with zero annotations, no output schema, and 13 all-optional parameters, the description is only partially complete: it lists what can change and notes the undo cost, but omits the partial-update contract and any permission/state prerequisites. Adequate but with a clear, agent-visible gap.

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 description coverage is only 31%, so the description must compensate, and it largely does: it groups width/height as 'size', workAreaStart/workAreaDuration as 'work area', and maps 'current time' to the time parameter, covering nearly all 13 fields conceptually. It stops short of adding semantics beyond naming (e.g., units for duration or frame rate), which the schema also omits.

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?

Specific verb ('Change') plus resource ('composition settings') and an enumeration of exactly which settings: size, duration, frame rate, background color, motion blur, shutter angle, work area, current time. It distinguishes itself from ae_create_comp by verb alone, though it never names that sibling 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?

Usage is implied rather than stated: 'Change' signals a modify-existing-comp operation, and 'open: true opens it in the viewer' hints at a variant workflow, but there is no when-to-use/when-not framing and no mention of ae_create_comp as the alternative for new comps. The 'omit to use the active composition' hint lives in the schema, not the description.

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