get_defaults

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

With no annotations, the description carries the full burden and exceeds it. It discloses persistence semantics (runtime vs config file), type coercion rules ('booleans/numbers are NOT coerced from strings'), timing effects ('takes effect on the next frontend load/refresh'), return shape ('{ id, previous, value }'), and availability constraints. There is no contradiction with annotations.

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 carries distinct, non-redundant information. It is structured with clear action bullets, a precedence list, and known-id examples, making the density acceptable. It is appropriately front-loaded with the core 'two separate stores' concept, so a reader can quickly grasp the main idea.

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?

Given the tool's complexity (4 actions, 6 params, nested objects, no output schema), the description is remarkably complete. It covers return values where relevant, known UI ids, edge cases like 'keys never written by the user are absent', and operational prerequisites. Any minor gaps (e.g., exact return of 'set') are negligible given the overall thoroughness.

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?

Though schema coverage is 100%, the description adds significant meaning beyond the schema. It explains conditional parameter requirements per action, clarifies that 'values' keys are 'typically lowercase' and NOT Comfy.* ids, defines filter as a case-insensitive substring, and details the exact types expected for set_ui values. This goes far beyond the schema's baseline.

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, salient summary: 'Read and write settings — either OUR generation defaults or ComfyUI's own frontend UI settings.' It then enumerates four distinct actions, each with its own verb, target store, and behavior, making the tool's purpose unmistakable and clearly distinguishing it from any sibling.

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 guidance is explicit and operational: it says when to use 'set' ('to avoid repeating common values'), when 'get_ui' is unavailable ('not available in Comfy Cloud mode'), and that 'get_ui'/'set_ui' target a 'DIFFERENT store' from 'get'/'set'. It even explains precedence and fallback behavior, leaving no ambiguity about which action fits which scenario.

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