Create a pose-preserving key on one unlocked object’s track at an existing frame without per-channel keying. On timeout, read back before retrying.
Create a key on an isolated unlocked object's track at an existing frame, preserving pose. Not per-channel keying. Timeout means unknown outcome; read back before retrying.
| Name | Required | Description | Default |
|---|---|---|---|
| frame | Yes | ||
| scene | Yes | ||
| object | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=true, so safety profile is partly covered. The description adds meaningful behavioral context beyond that: the timeout-is-ambiguous failure mode and the read-back-before-retry guidance, plus the scope constraint that the object must be isolated and unlocked. It does not explain what the destructive annotation actually destroys or the effect on existing keys, so it falls short of 5.
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, front-loaded sentences with zero filler: the operation first, the keying-mode caveat second, the failure/retry rule last. Every sentence carries information an agent 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?
For a 3-param mutation tool with annotations and no output schema, the description covers scope, preconditions, and the critical ambiguous-timeout behavior. It is nearly complete; the main omission is any statement of what the destructive write affects or whether existing keys are overwritten.
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 0% for all three parameters, so the description must compensate. It adds real meaning for 'frame' (must already exist) and 'object' (must be isolated and unlocked), but says nothing about 'scene' or the accepted range/format, so it only partially fills the gap.
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: 'Create a key on an isolated unlocked object's track at an existing frame, preserving pose.' This is precise enough for an agent to know it sets a keyframe rather than a transform. It differentiates from per-channel keying ('Not per-channel keying') but does not name any sibling tool (e.g., set_transform) for contrast.
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?
Provides an implicit precondition ('at an existing frame', 'isolated unlocked object') and an error-handling rule ('Timeout means unknown outcome; read back before retrying'), which is genuinely useful. However, it never states when to choose this over sibling mutation tools like set_transform or set_pose, nor any explicit when-not condition beyond the keying-mode note.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.