decide

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

With no annotations present the description carries the full burden and does so: it discloses the single-forward-pass execution model, the deliberate absence of text generation/output parsing/retries, the 1–64 question cap, the server-side state read ('files never enter your context'), and the failure mode for non-decision models. This is behavioral context an agent could not get from the schema.

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?

Front-loaded with purpose, then constraints, then the routing rule, then question types and requirements — each sentence carries distinct information. It is dense rather than padded, though the type-semantics block could be tightened slightly given the schema already constrains the enum.

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 no output schema and a nested question object, the description still tells the agent what comes back (calibrated probabilities per option), what is required to run it, and how the nested question types behave. Nothing an agent needs to invoke it correctly appears to be missing.

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 86%, so the baseline is 3; the description goes beyond it by explaining the 'choice' / 'score' / 'noul' question-type semantics, including that `criteria` maps option keys to descriptions and that a null value falls back to the key. It clarifies the server-side meaning of the state parameters, though it leaves `glob`/`paths`/`provider` largely to 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?

Starts with a specific verb+resource ('Decision-model scoring'), names the endpoint and the concrete models (clef / clef-flash / nimble / tev), and states the output ('calibrated probabilities per option'). It also explicitly distinguishes itself from the sibling `classify`, so an agent can pick between them without opening either schema.

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?

Gives an explicit routing rule ('Prefer over `classify` when a decision model is available: you get real probabilities instead of parsed JSON') plus a hard precondition ('Requires an ollama provider running a decision model; a normal chat model returns an error'). Both when-to-use and when-it-fails are covered.

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