Script Info

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

With no annotations provided, the description carries the full behavioral disclosure burden, but it merely reveals the HTTP method (GET, implying a read-only operation) without disclosing authentication requirements, error behavior, response shape, or other side effects. The description provides only marginally more than the bare endpoint documentation and adds little beyond what one would assume.

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?

One efficient sentence with zero wasted words, and the endpoint is front-loaded for quick scanning. It loses one point for being so brief it borders on under-specification — an additional phrase could have done a lot of work — but strictly evaluated on conciseness, there is nothing extraneous.

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 2 parameters, zero annotations, and no output schema, the description should carry significant contextual weight, but it doesn't. It fails to explain what a 'script' is in this domain, what the img2img parameter does, a potential filter, or what the single script name should reference. The bare endpoint is helpful only to those already familiar with the API.

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 only 50% — 'name' gets a tautological 'Script name.' description and 'img2img' has none at all. The description adds zero parameter context, failing to clarify what img2img does (e.g., whether it scopes scripts by mode) or what values name accepts. The description was the only chance to compensate for the thin schema and did not.

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 uses a specific verb-resource pair ('Get info for a single script') that clearly distinguishes it from list-style siblings like sdnext_list_scripts. The inclusion of the HTTP endpoint (GET /sdapi/v1/script-info) adds precise, actionable context. This unequivocally states what the tool does and how it differs from nearby tools.

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 word 'single' implies a contrast with list operations, suggesting the user should use this only for one script at a time, but it never explicitly says when to use this vs. alternatives like sdnext_list_scripts, nor does it describe any exclusions or prerequisites. The usage context is implied rather than stated.

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