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

With only readOnlyHint=false and destructiveHint=false in annotations, the description carries the full burden and delivers extensively. It discloses creation semantics, default values, the autofit modes' precise behavior (including the guarantee that 'hug' prevents re-wrapping between preview and export), curve direction conventions, and the return value. It even explains the legacy 'shrink' mode. Nothing is left opaque.

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 long but every sentence earns its place given the 23 parameters and complex behaviors. It front-loads the core purpose and then covers defaults, styling, autofit modes, and return value in a logical order. It is dense but not redundant; minor verbosity in the autofit explanation is justified by its importance.

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 tool with 23 parameters, nested objects, an output schema, and rich sibling interactions, the description is comprehensive. It covers defaults, behavioral nuances, return value, and critical caveats (e.g., curve only works on single lines). An agent can confidently invoke this tool without needing to consult other 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 description coverage is 100%, so every parameter already has an explanation in the schema. The description adds some nuance (e.g., explaining the rationale for hug mode and pairing with set_text_background), but it largely repeats the schema's parameter details. It does not significantly compensate beyond what the schema provides, so the baseline 3 is appropriate.

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 pair ('Create a new text layer') and immediately qualifies it as a 'first-class leaf that animates, groups, and z-orders exactly like an image or shape,' which clearly separates it from siblings like add_caption_track or set_layer_text. It also enumerates the full styling surface, so an agent knows exactly what this tool is for.

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 states what the tool does and hints at usage contexts (e.g., 'what an agent-placed watermark / lower-third almost always wants' in the block parameter), but it never explicitly contrasts it with alternatives or says when not to use it. There is no 'use add_caption_track instead' type guidance, so the when-vs-other-tools decision is left implicit.

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