list_inference_requests

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context by indicating that returned requests are 'prompt-free,' have exactly one typed outcome, and exclude derived status fields. However, it does not disclose ordering, cursor behavior, empty-result behavior, or what happens when run_id is invalid, though these are partially mitigable by the output schema.

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 a single sentence with no filler, and the primary action 'Page through' is front-loaded. It is compact and avoids repetition of the tool name or schema details. The dense qualifying phrase 'with one typed outcome and no derived status fields' is efficient but slightly hurts readability.

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 read-only paginated list operation, the description is minimally adequate given the rich annotations and the presence of an output schema. However, it does not explicitly tie the required run_id to the scope of the listing, and it never explains what an 'inference request' is in this context. A sentence clarifying that this paginates requests for the given run would make it complete.

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 0%, so the description must compensate for undocumented parameters, but it does not. 'Page through' hints at limit and cursor usage, yet run_id—the only required parameter—is never explained, and cursor semantics are left entirely to inference. The description adds minimal value beyond the bare field names in 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 names a specific action ('Page through') and a specific resource ('prompt-free requests'), which distinguishes it from sibling list tools like list_inference_configurations and list_runs. The phrase 'with one typed outcome and no derived status fields' adds detail about what kind of requests are returned, though it is somewhat jargon-heavy and assumes domain knowledge.

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 no guidance on when to use this tool versus alternatives such as list_inference_configurations, list_runs, or list_artifacts. It does not state any exclusions, prerequisites, or explicit conditions like 'use this to enumerate inference requests for a specific run.' The only implied context is pagination from 'Page through.'

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