Run Status

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description builds on that by explaining the durable-state semantics, the derived polling fields, and the exact terminal-state vocabulary. This adds useful behavior beyond the annotation flags without contradicting them.

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 key action is front-loaded in the first line and the supporting facts (derived fields, terminal states, log sibling) are compactly grouped. Every sentence carries distinct information with no filler.

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?

With an output schema present, the return-value details are not the description's job; it supplies the run-state vocabulary, polling fields, and a pointer to get_run_logs. It is complete for a simple single-parameter read operation, though it could have noted the source/format of job_id.

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?

There is one required parameter, job_id, and schema description coverage is 0%; the description never explains what job_id is, where it comes from, or its expected format beyond the schema's property name. The parameter is self-descriptive, but the description does not compensate for the lack of any schema-level documentation.

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?

Starts with a precise verb-resource pair: 'Read the durable state of a product-owned asynchronous run.' It also distinguishes itself from get_run_logs by noting that log_uri belongs to the log tool, and enumerates terminal states, so an agent can tell status from result/log tools.

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 usage context for polling a run: it is read-only, includes derived polling fields (elapsed_seconds, eta_bound), and points to get_run_logs as the sibling for log content. It does not explicitly list when-not-to-use conditions versus get_run_result, but the context is strong enough.

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