sonar_async_submit

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

With no annotations, the description carries the full burden. It correctly discloses the async behavior (returns request_id for polling) and references the POST endpoint. However, it omits any mention of side effects, rate limits, error handling, or whether the job is persisted. It adds basic behavioral context but not enough for a fully informed agent.

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 extremely concise, two sentences, and directly front-loaded with the core purpose. It includes the endpoint, the return type, and the intended use case without any redundant words.

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?

Given the complexity (12 parameters, no annotations, no output schema), the description is far too sparse. It only explains the submit-and-poll flow and misses critical details about message formatting, search filters, or error responses. For a tool with this many options, the description is not sufficient for correct usage in most scenarios.

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% and the description provides no parameter explanations. The only parameter-related hint is 'Ideal for sonar-deep-research model', which aligns with the default but does not explain any of the 12 parameters like messages, search filters, temperature, or max_tokens. The description adds virtually no value beyond 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?

The description clearly states a specific verb ('Submit') and resource ('asynchronous deep research job'), names the exact API endpoint, and distinguishes this from siblings by emphasizing the asynchronous nature and the returned request_id. It is specific enough to be differentiated from sonar_chat or sonar_async_list.

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 provides clear context for when to use this tool (for async deep research jobs) and explicitly directs the agent to poll with sonar_async_get. It also suggests 'sonar-deep-research' as the target model. However, it does not explicitly state when not to use it or mention synchronous alternatives.

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