jev_decide

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context: no tools are executed, the request limit is 64 KiB, and 'Noul is a probability, not a severity score.' These details go beyond the annotations and help the agent understand side effects and semantics. It doesn't describe response format, but the output schema exists and the description covers the key behavioral traits.

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 compact and front-loaded: the core action and constraint (1–32 questions, no tool execution) appear in the first sentence. The question format examples are dense but necessary, and the final two sentences add critical limits and semantics. Every sentence earns its place; no filler.

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 required params, no enums, and an output schema, the description covers the essential usage: what to send, the question format, the count limit, the request size limit, and the no-execution guarantee. The main gap is that it doesn't describe what the response contains or how to interpret the returned decisions, but the output schema likely covers that. It also doesn't explicitly state when to prefer this over jev_route/jev_triage, but the sibling list is large and the description is otherwise sufficient.

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 0%, so the description must compensate. It does: it explains the 'state' parameter implicitly as 'explicit state' and gives concrete shapes for the 'questions' parameter with three question types (choice, noul, score) and their fields. It also clarifies the noul semantics. This is strong compensation, though it doesn't fully document every possible field of the questions object.

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 states a specific verb ('Send explicit state and 1–32 Choice/Score/Noul questions to Jev') and identifies the resource (Jev) and the question types. It also explicitly says 'No tools are executed,' which helps distinguish it from sibling tools that apply or preview workflows. However, it doesn't explicitly name a sibling alternative or contrast with jev_route/jev_triage, so it falls short of full differentiation.

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 gives clear context: it is for sending state and questions to Jev, with a limit of 1–32 questions and a 64 KiB cloud request limit. It also clarifies that no tools are executed, implying it is a decision/consultation tool rather than an execution tool. It does not explicitly state when to use this instead of jev_route or jev_triage, so it lacks explicit exclusions.

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