Get Run

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

Annotations already mark readOnlyHint=true, and the description does not contradict that. It adds useful behavior beyond the annotation: the receipt is 'persistent' and scoped to 'the authenticated caller,' clarifying retention and access boundaries. It could mention error behavior for invalid run_id, but the readOnly annotation and output schema cover much of the safety profile.

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?

A single ten-word sentence, front-loaded with the action and object, with no filler. Every phrase ('persistent,' 'owned by authenticated caller') adds meaning.

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 read tool, the description plus full schema and output schema is nearly complete; it tells the caller the receipt is persistent and access is caller-scoped. It is slightly thin on when to call it and what 'receipt' entails, but the schema's run_id description ties it to submit_code/execute_code.

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?

The input schema fully describes run_id as the handle returned by submit_code/execute_code, so schema coverage is 100%. The description's phrase 'run receipt' loosely echoes that parameter but adds no new syntax or format details; 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?

The description names a specific verb ('Read') and resource ('persistent run receipt') plus an ownership constraint ('owned by the authenticated caller'). This clearly separates it from run-producing siblings like execute_code/submit_code and from cancel_run.

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 implies the use case: retrieve a previously created run receipt for the caller's own run. It does not explicitly state when to prefer this over get_functions/search_functions or give a 'do not use when...' exclusion, so guidance is only implied.

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