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

Annotations already declare readOnlyHint=false and openWorldHint=false, so the safety profile is partly carried. The description adds nothing about reversibility (is this undoable?), whether clearing is lossy, or what happens to the property's current animated value. It also sits oddly against destructiveHint=false, since removing all keyframes on a property discards data — worth flagging as a mild inconsistency rather than a hard contradiction.

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 with zero filler; the verb and resource lead. It is arguably over-terse rather than bloated, so brevity is not the problem — missing content is.

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 three-parameter mutation with no output schema, the definition is thin: it omits the clear_keyframes vs. remove_keyframe boundary, reversibility, and whether projectId defaults to the open project (only the schema notes that). It gives just enough to call the tool, not enough to call it confidently.

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 33% (only projectId is documented), so the schema does not fully carry the load. The phrase "one property or all" does usefully clarify that prop is optional and that omission clears every property, which the schema alone leaves implicit — but clipId and the prop enum values get no added meaning.

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 names a specific verb and resource ("Remove keyframes") and adds a scope hint ("one property or all"). It does not, however, distinguish itself from the sibling remove_keyframe, which appears to do nearly the same thing at a narrower granularity, so the agent must infer the split.

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?

There is no explicit when-to-use guidance, no prerequisites (e.g. a clip must be selected or clipId valid), and no named alternative. The parenthetical hints that omitting the property clears everything, but the reader is left to infer why one would pick clear_keyframes over remove_keyframe.

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