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

No annotations are provided, so the description carries the full behavioral burden. It discloses defaults (centre x/y, 900x320, Anton, derived text_size), mutation semantics (creation + returned id), timing behavior (omitting block = always present, keyframes relative to `start`), curve direction conventions (positive = smile, negative = arch), and edge cases (decorations not rendered on curved text). This is unusually transparent for a create tool.

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 description is dense and well-structured, front-loading the core action and then layering defaults, styling options, and return value. It is long, but every section adds operational value. The only minor redundancy is that some parameter details (e.g. autofit semantics) are repeated in the schema, but in context this repetition helps an agent avoid schema-diving.

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 23-parameter creation tool with no output schema and no annotations, the description is remarkably complete. It covers defaults, derived behaviors, keyframe timing semantics, curve constraints, autofit modes, return value, and edge cases. An agent has enough context to call this correctly and interpret the result without auxiliary documentation.

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 substantial meaning beyond the schema: concrete defaults (canvas centre, Anton, 900x320, derived text_size), the practical watermark/lower-third use case for omitting `block`, the live shrink-wrap guarantee of 'hug', the smile/arch convention for `curve`, and the return value. This far exceeds what the schema alone communicates.

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 opens with a specific verb+resource: 'Create a new text layer'. It further distinguishes this tool from siblings by characterizing the layer as 'a first-class leaf that animates, groups, and z-orders exactly like an image or shape', and by stating the renderer draws 'live typeset text'. This makes it clearly distinct from add_image_layer, add_shape, set_layer_text, and add_caption_track.

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?

The description gives strong parameter-level guidance, such as omitting `block` for watermark/lower-third overlays and using specific autofit modes, but it never explicitly tells an agent when to choose add_text_layer over sibling tools like add_caption_track or add_image_layer. Usage is implied by the tool's purpose rather than declared with exclusions or alternatives, so this is adequate but not exemplary.

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