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

Annotations already declare readOnly=false, idempotent=true, destructive=false, and closed-world, so the safety profile is covered. The description adds genuine value by saying the output is editable native text/vector rather than baked pixels and that 'replaces' is possible, but it omits permissions, what happens to an existing graphic of the same id beyond replacement, and nothing about the motion/caption behavior of the 17 parameters.

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?

Two sentences, front-loaded with the core action and supporting detail, with no filler. Dense but not padded; it could be slightly tightened but every clause carries 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?

This is a high-complexity mutation tool with 17 parameters, five enums, six required fields, no output schema, and almost no schema documentation. Two sentences cannot equip an agent to populate font_size, treatment, fit, motion, or the timing range correctly, leaving most required decisions guesswork.

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 6% across 17 parameters, so the description carries the burden here and largely fails. It gestures at the kind enum and at text plus 'layout geometry' (presumably box), but fit, treatment, palette, font_size, eyebrow, secondary, speaker, motion, motion_motif, mute_captions, and the start/end timing fields receive no explanation in either the schema or the description.

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 gives a specific verb pair ('creates or replaces') and a named resource ('identified editorial composition') plus the implementation approach ('editable native text and vector layers'). The enumerated forms (statement, comparison, metric, quote, chapter, label, headline) map directly to the kind enum and help distinguish it from generic text/vector siblings, but it never names those siblings, so differentiation still requires 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?

There is no when-to-use or when-not-to-use guidance and no reference to alternatives such as set_vector_graphic, add_text, set_typeset, or set_typography_scene, all of which occupy adjacent territory. An agent knows what the tool makes but not when to prefer it over those siblings.

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