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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it discloses the response shape ('`choices[0].message.content`, `citations`, `search_results[]` and `usage` out'), the measured latency ('about 5 seconds'), and the flat pricing ('$0.012 per request'). It also clarifies the reasoning behavior ('step-by-step answer backed by web search'). The only minor gap is that it doesn't mention streaming behavior, but the schema covers `stream`.

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 three sentences with zero waste. The first sentence front-loads the core purpose and behavior, the second adds the response shape and cost/latency, and the third routes to alternatives. Every sentence earns its place.

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 13-parameter tool with 100% schema coverage, an output schema, and rich annotations, the description is complete. It covers what the tool does, when to use it, what comes back, and how it differs from siblings. An agent has everything it needs to select and invoke this tool correctly.

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 100%, so the schema already documents all 13 parameters. The description adds the key semantic constraint that `model` is required and should be `sonar-reasoning-pro`, and it names the output fields. However, it doesn't add meaning to parameters like `search_context`, `top_k`, or `temperature` beyond what the schema already provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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 opens with a specific verb ('Ask a question that has to be worked through') and a clear resource ('Sonar Reasoning Pro'), and immediately distinguishes it from siblings by naming the faster `post_perplexity_sonar` and the longer `post_perplexity_sonar_deep_research`. The phrase 'chain-of-thought reasoning with search' in the title is reinforced by the description's focus on step-by-step answers backed by web search.

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 explicitly states when to use this tool: 'Use it for comparison, causation and analysis.' It also gives exclusions: 'When the question is simply what is the case, `post_perplexity_sonar` is faster; when you need a long report over many sources rather than an answer, `post_perplexity_sonar_deep_research`.' This is a textbook example of when/when-not guidance with named alternatives.

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