run_inference_profile

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

Annotations indicate readOnlyHint=false, idempotentHint=false, and destructiveHint=false, and the description adds only 'diagnostic-only' and 'one ... profile window.' It does not disclose what side effects occur on the managed vLLM server, whether it blocks until completion, or whether it creates artifacts or state. There is no contradiction with the annotations, but the behavioral burden is not fully met.

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, front-loaded sentence with no filler words. Every part—'run,' 'one,' 'diagnostic-only,' 'profile window,' 'managed vLLM server'—carries meaning, making it highly scannable for an agent.

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?

Even with an output schema present, the tool requires plan_token, and nothing explains what a plan token is, how to obtain it, or what expected_plan_id validates. The description does not define 'profile window' or mention the relationship to the planning workflow, so an agent would still have significant ambiguity in invoking it 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 0%, and the description does not mention plan_token or expected_plan_id at all. An agent is left to infer that plan_token is a 64-hex token and expected_plan_id is a nullable sha256 identifier, but the description provides no semantic meaning, origin, or relationship between them.

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 uses a specific verb ('Run') and a specific resource ('one diagnostic-only profile window against a managed vLLM server'), so an agent can tell this executes a profile rather than plans or configures one. It distinguishes itself from siblings like plan_inference_profile and run_inference_scenario at a surface level via 'profile window' and 'diagnostic-only', but it does not explicitly name or contrast those alternatives.

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 gives no guidance on when to use this tool versus run_inference_scenario, plan_inference_profile, or other inference family tools. It also does not state that plan_token is likely produced by a planning step or that this should run after plan_inference_profile, leaving prerequisites and tool-selection context unstated.

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