set_storyboard

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

Annotations already declare readOnly=false, destructive=true and openWorld=true, and the description goes well beyond that: it states this 'replaces the earlier storyboard', that existing sketches are kept while new/changed ones render in the background (~30 s), that omitted 'variants' are preserved, and that a new Higgsfield/Replicate clip demotes the old one to a variant. That is the kind of mutation/async disclosure the annotations cannot carry.

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 purpose is front-loaded, which is good, but everything after it is one dense unbroken block covering shots, scripts, sketches, videos, variants, takes, comments and format. Several phrases duplicate the schema verbatim (e.g. 'never text in the frame', 'word for word from script.md'), so not every sentence fully earns its place.

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 complex, destructive, no-output-schema write tool this covers the essential ground: what gets overwritten, what is preserved, async timing, the no-image-key failure mode and who to ask, plus how takes and comments tie back via get_session. An agent has enough to invoke it correctly without guessing.

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 100%, so the baseline is 3, but the description adds real meaning: the 'image' fallback path when no image key exists, the ordering/selection semantics of 'variants' vs 'video', the persistence rules for 'format' across calls, and the fact that ids must be preserved so takes and comments still match. It is richer than the schema alone, though it leans on the schema for field-level detail.

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?

Opens with a concrete verb+resource ('Write the session's storyboard') and immediately defines the artifact as a row of shots shown as a horizontal timeline. It also distinguishes itself from the read path by pointing at get_session's 'storyboard' for ids, takes and comments, so an agent can tell write from read without opening a schema.

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?

Gives a clear activation condition ('use it with the storyboard skill when the user brainstorms a video idea') and names get_session as the read counterpart, plus per-case guidance (redraw=true to redraw, no image key → ask the user or pass your own sketch). It stops short of an explicit 'do not use this when…' exclusion, which keeps it at 4 rather than 5.

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