PayperDecision

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

With readOnlyHint=true already covering safety, the description adds substantial extra context: default and named models, per-call limits (64 questions, 2-20 options, 2-10 levels), billing behavior ('charged only if the model call succeeds'), a pricing formula with a $0.001 minimum, and the explicit caveat that answers are probabilities, not verified facts. It also discloses the current limitation that images are not accepted.

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 the core action, then dense but purposeful clauses covering types, limits, models and billing; every sentence adds information. It is a long single block, and the pricing arithmetic in the middle slightly interrupts the selection-relevant flow, but there is 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?

No output schema exists, and the description compensates by describing answer shapes per question type (probability of yes, option name plus per-option probability and confidence, probability-weighted level). Combined with the billing and caveat information, an agent can call this correctly; only the undocumented 'state' payload leaves a real hole.

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 0%, so the description must carry the load, and it largely does: it defines the questions map shape, the id key format implication, each type's criteria structure and cardinality limits, and the model parameter's valid values plus default. The one gap is 'state', whose schema is an untyped empty object and which the description never explains or gives an example structure for.

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?

States a specific verb and resource ('Answer typed questions about a state with probabilities') and pins the modality ('in one pass and no generated text'). It is clearly distinguishable from the sibling 'models' tool, which presumably lists models rather than answering questions.

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 per-type explanation (noul, choice, score) implicitly tells an agent which question type fits which intent, and the pricing/caveat sentences set context. However, there is no explicit when-to-use/when-not guidance and no named alternative, so usage must be inferred rather than read.

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

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

Annotations already establish readOnlyHint=true, so the safety profile is covered. The description adds genuinely new behavioral context by disclosing the cost model ("Free") and the exact contents of the response, which matters because there is no output schema to describe return values. It stops short of stating rate limits or whether pricing varies per model.

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 sentence carries the payload detail and the front-loaded verb plus resource tells the agent immediately what happens. The one-word "Free." fragment is terse but pays for itself by flagging cost.

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?

With zero parameters and no output schema, the description carries the burden of describing what comes back, and it does so by listing the specific fields returned. The only missing piece is an explicit pointer to the `decide` sibling as the follow-up action.

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 tool takes zero parameters, so the baseline applies; there is nothing for the description to disambiguate. The description's mention of rates, formula, limits, and request/answer shapes is about output rather than input, leaving parameter semantics trivially satisfied.

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?

Names a specific verb and resource ("List the decision models") and enumerates the payload contents an agent will get back: rates, pricing formula, limits, and request/answer shapes. It does not name the sibling `decide` tool, so the boundary between discovery and execution is only implied by the word "Free".

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 single word "Free" hints that this is the no-cost exploration call before invoking the paid `decide` sibling, which is a useful implicit signal. However, there is no explicit when-to-use or when-not-to-use statement, and the alternative tool is never named.

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