decide

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

Annotations already indicate readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'Files are not modified.' It goes beyond annotations by disclosing that local files are read and sent to a decision server, that probabilities are uncalibrated and normalized within supplied candidates rather than factual correctness, and that the assistant should explain this when asked rather than repeating disclaimers.

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 core purpose is front-loaded in the first sentence, and each following sentence adds schema or behavioral detail without padding. The middle is dense and somewhat run-on, but every clause provides useful information, so it earns a high score.

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?

The description covers the essential inputs and output categories, but because there is no output schema it does not fully explain the exact result structure beyond 'decisions and elapsed seconds.' It also omits documentation for several request subfields, leaving the tool workable but not fully complete for complex calls.

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?

With schema description coverage at 0%, the description carries the burden and does meaningfully explain request.questions mappings, choice and score criteria structure, state, sources_only, and image/state_files. However, it leaves request.mode, request.seed, request.samples, and request.rag without any explanation, creating a notable gap for an agent trying to use all options correctly.

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 and resource: 'Return yes/no (noul), choice or score decisions and elapsed seconds using DiffusionGemma.' It clearly identifies what the tool produces and distinguishes the decision types, making the purpose unmistakable even without a title.

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 provides conditional usage cues such as 'state is optional evidence' and 'sources_only:true restricts evidence,' and explains when image/state_files are relevant. However, there is no explicit statement of when to prefer this tool over alternatives or when not to use it, and no sibling tools are named.

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