get_history

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

With no annotations, the description fully discloses the tool's return contents (raw error/traceback included) and its limitations (no missing models/node types). It accurately portrays the tool's capabilities without hiding constraints.

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 concise (~100 words) and well-structured: first states purpose, then differentiates from sibling, then details parameter behavior. Every sentence adds value with no redundancy.

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 no output schema, the description enumerates expected return fields (status, timing, cached nodes, output filenames, error/traceback) and positions the tool relative to `diagnose_run`. This equips the agent to interpret results and choose correctly among 100+ siblings.

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?

The schema already fully documents the `prompt_id` parameter (100% coverage). The description adds useful behavioral context about omission behavior and a brief lag note, adding value beyond 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?

The description clearly states the tool retrieves execution history for a ComfyUI prompt, listing specific data types (status, timing, cached nodes, output details). It distinguishes from sibling `diagnose_run` by noting what each tool covers, making purpose and scope unambiguous.

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?

Explicit guidance is provided: use `get_history` for outputs/timing, and prefer `diagnose_run` for failure diagnosis or missing models/node types. This directly helps the agent decide which tool to invoke.

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