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

Annotations already declare readOnly=false and destructive=false, so the agent knows this is a non-destructive mutation. The description adds genuinely useful behavior beyond that: effects stack arbitrarily, apply in order, keying is forced last, and omitted params fall back to defaults. It does not describe what is returned or what happens if an invalid effect/param combination is passed.

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 core action, then dense semicolon-delimited type documentation with no filler sentences; every clause carries specification. The wall-of-text effect catalogue is hard to scan, but trimming it would cost real information.

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 6-parameter mutation with a nested free-form params object and no output schema, the description covers the hard part (effect types and their arguments) thoroughly and explains stack ordering. It is incomplete on the clipId/clipIds duality and on what the call returns, which matters since there is no output schema to fall back on.

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 only 33%, and the schema's params object is an untyped grab-bag, so the description carries the load by enumerating every effect type's parameters with ranges (e.g. brightness -1..1, chromaKey similarity 0.01..0.6, mirror axis enum). That is substantial added meaning. The gap: clipId vs clipIds (single vs multiple clips) and projectId are never explained, leaving two of six parameters ambiguous.

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?

"Stack an effect on video/image clips" gives a specific verb (stack/add) and resource (effect on clips), plus the full enum of supported effect types, so an agent knows exactly what lands where. It does not explicitly contrast itself with update_effect, move_effect, copy_effects or clear_effects, so sibling differentiation is left implicit.

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 by the verb: use this to add a new effect rather than modify one. The ordering rule (applied in order, keying always runs last) and "any number per clip" give real usage context, but there is no statement of when to prefer update_effect, move_effect or batch_edit, and no prerequisites (e.g. clip must exist, project must be open).

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