infer

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

With no annotations, the description carries full behavioral burden. It mentions the list_services prerequisite but omits async behavior (wait=0), result retrieval via get_request_status, timeout handling, and output format. These are significant gaps for an inference tool that suports multiple models.

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?

Two sentences with a clear purpose and a critical prerequisite. The 'IMPORTANT' caps are slightly noisy but the content is focused and front-loaded. No wasted 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?

For a 5-param tool with nested input and no output schema or annotations, the description doesn't explain the response format, async workflow, or how to retrieve results. The list_services note helps, but the agent is left without a complete picture of how to correctly invoke and consume this tool.

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 baseline 3 applies. The description's list of supported tasks (image gen, transcription, text gen) hints at what input may contain, but it adds no concrete parameter-level details beyond what the schema already states. Service param already points to list_services.

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: 'Run AI inference on a Theta EdgeCloud model.' Lists supported task types (image generation, audio transcription, text generation). Sibling names (list_services, get_request_status, get_upload_url) make the distinction clear implicitly, though the description does not explicitly name them.

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?

Explicitly instructs the agent to 'Call list_services first to see available services and their required inputs,' which is a clear prerequisite and routing to a sibling tool. It does not discuss exclusions like when to use get_request_status instead, so it's a bit incomplete on alternatives.

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