get_run_results

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

Annotations already declare readOnlyHint=true, and the description adds genuinely new behavioral context beyond that: 'Free: no new run is started', which tells the agent this poll costs nothing and does not re-trigger work. It does not describe what the result payload contains, but it covers the cost/idempotency trait that matters most for a polling call.

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 short sentences, front-loaded with what the tool does and followed by the cost behavior. Nothing is redundant and no padding is present.

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 one-parameter async polling tool with full schema coverage and a documented read-only annotation, the definition supplies everything needed: the trigger condition, the argument source, and the fact that it is free. No output schema exists, so return-shape documentation is not required.

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 100% with a single required parameter whose schema description already says it is 'the runId returned by a previous tool call.' The description restates that origin, adding no syntax, format, or edge-case detail beyond the schema, so the baseline 3 applies.

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 (fetches the results of a previous call) plus the qualifying condition that the call was still running. This is unambiguous and clearly distinguishable from every sibling tool, which are all discovery/search tools rather than an async continuation endpoint.

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?

Gives an explicit trigger condition ('a previous call that was still running when it returned') and tells the agent where the argument comes from ('use the runId it gave you'). No alternatives or exclusions are named, but no sibling occupies this niche, so the omission is minor.

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