Perplexity

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

Annotations already declare readOnly, non-destructive, open-world behavior, so the safety profile is covered. The description adds genuinely useful context the annotations do not: statelessness (no conversation history), one prompt per call, JSON-parsed output. It omits anything about credentials, quotas, latency, or failure modes, which is a real gap for a third-party scraping proxy.

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?

Three short sentences, front-loaded with the action and the stateless constraint, with the docs URL relegated to the end where it belongs. The only cost is that the docs link occupies a sentence without conveying behavior itself.

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 two-parameter, no-output-schema tool, the description covers what matters: single-turn behavior, that the answer comes back as JSON, and that sources are part of the value. Slight incompleteness in not sketching the JSON payload (answer field, sources field) or noting the stateless implication for follow-ups.

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% for both parameters, so the structured data already documents `prompt` and `geo`; the baseline of 3 applies. The description adds no meaning beyond the schema — nothing about prompt length limits, what a country name does to results, or the default when `geo` is omitted.

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 pairs a concrete verb (send a prompt) with a concrete resource (Perplexity via Decodo's `perplexity` target) and states the return shape (answer parsed as JSON). It does not name the obvious sibling `chatgpt`, which is the main thing keeping it from a 5, since an agent must infer the differentiation itself.

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?

It gives one positive use case ('see how Perplexity answers a question and which sources it draws on') plus an implicit constraint (single prompt, no conversation history). There is no when-not guidance and no explicit alternative such as `chatgpt` or `search`, so selection against siblings rests on inference.

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