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

Annotations already flag this as non-read-only and destructive; the description adds genuinely new behavioral facts — that the mutation costs exactly one undo step, that undo_storyboard reverses it, and that it consumes no credits (a meaningful signal among credit-spending siblings like generate_image). It does not clarify whether the destructiveHint applies because prior values are overwritten, nor what happens if a type-mismatched field is supplied.

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 tight clauses: what changes, how it is reversible, and what it costs. The resource and mutation come first, with cost/reversibility trailing. No filler sentences.

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?

With annotations covering safety and an output schema covering returns, the description supplies the remaining essentials: mutation semantics, reversibility, cost, and field/type mapping. Minor gap: it doesn't say whether unmentioned fields are left untouched or whether passing color on a text id errors — useful for a partial-update tool but not blocking.

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 60% (text and storyboard_id carry no descriptions), and the description compensates by mapping fields to element types: 'its words' → text, 'a note's color' → color, 'a text's size' → size. It also explains that the id comes from the brief and is prefixed note_…/text_…, reinforcing the schema pattern. It leaves the storyboard_id parameter and the 500-char limit to the schema.

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 ('Change'), a precise singular resource ('one note or text element on a film's canvas'), and enumerates the mutable fields (words, note color, text size). The verb 'change' plus the id-prefix constraint cleanly separates it from add_storyboard_note, add_storyboard_text and remove_storyboard_annotation without needing to name them.

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 rather than stated: it's clear this edits an existing element rather than creating one, and 'by the [id] the brief prints' tells the agent where the identifier comes from. The only explicit alternative named is undo_storyboard as the rollback path; there is no statement about when to prefer update_storyboard (canvas-level) or the add_* siblings.

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