Perplexity Decide

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

Annotations only give readOnlyHint=false/openWorldHint=true/destructiveHint=false; the description goes well beyond by disclosing the cost model ($0.02/M input tokens, free output), that refused calls cost nothing, and that every API-reaching request is recorded as spend with a pointer to perplexity_usage. It stops short of auth or rate-limit details, so not a 5.

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 the three answer modes, then the cost caveat — each sentence carries information. Somewhat dense and long, but no sentence is filler; the 'probabilities not facts' clause is a genuine usage qualifier.

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 a full input schema and an output schema, the description covers the essentials: what goes in, what comes out conceptually, and the billing consequence of calling it. Missing only operational detail (auth, rate limits, error behavior) that would push it to 5.

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 100%, so baseline is 3; the description adds real value on top by explaining the semantics of the three question types (yes probability, most-probable option, weighted position on an ordered rubric) and that one call holds many questions. The model/state/project parameters are left entirely 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?

States a specific verb and resource ('put typed questions about a text to the Decisions API') and enumerates the three answer modes (noul/choice/score) with what each returns. An agent can distinguish this from perplexity_ask or perplexity_chat without opening a schema — this is classification, not generation.

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 line 'The answers are model probabilities, not facts: you choose the threshold' implies when this tool is appropriate (calibrated judgment rather than factual answers), which helps route away from ask/chat/research. However, no sibling is named and there is no explicit when-not guidance, so usage must be inferred.

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