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

Annotations only carry the safety profile (not readOnly, not destructive, not idempotent). The description adds genuinely non-structured traits: project scoping ('acts only on the explicit project_id and returns the project identity'), timeline-neutrality ('sound and timing untouched'), and a flash-safety policy requiring the user's consent above 3 changes/second.

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?

The scoping constraint is front-loaded and every clause carries information (frames formats, enums, safety). It is dense and slightly packed, but there is little 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 10-parameter tool with nested objects and no output schema, the description covers the effect model, most parameter formats, scoping, and the safety policy. Remaining gaps are start/end time units and as_insert behavior.

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?

At 10% schema coverage the description must compensate, and it largely does: it explains frames entry types (media keys, 'src:<seconds>', 'program', colours, {source, hold_f, negate}), hold range, pattern cycling, negate values, fit including 'register', and that variant_set uses make_variant_set. Gaps remain: start/end units are ambiguous and as_insert is undocumented.

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+resource ('A frame-exact strobe over start-end') and defines the effect precisely (images held hold frames, cycled by pattern). It does not explicitly differentiate itself from the many add_* effect siblings (add_finish, add_stylize, add_corrupt_screen), so sibling disambiguation is left to inference.

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 effect semantics and one constraint is given ('More than 3 changes a second needs the user's ask'), but there is no explicit when-to-use vs alternatives guidance or which sibling to prefer. An agent can infer the context but is not routed.

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