get_run_control

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 agent knows this is a safe read operation. The description adds that it returns 'durable lifecycle status' and mentions specific state elements (revision, checkpoint, cancellation, next stage), which adds some behavioral context about what gets returned. But it doesn't describe ordering, staleness semantics, or synchronization behavior of the control state.

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?

One tight sentence that enumerates the key data fields with zero filler. Efficiently front-loads the tool's purpose and scope without waste.

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?

This is a simple tool (1 param, no nested objects, output schema present). The presence of an output schema reduces the need to explain return values. However, with a read-only informational tool that has no annotation contradictions and simple schema, the description is adequate but not rich; it could benefit from noting whether the data reflects immediate or persisted/settled state.

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 schema has one parameter (run_id) at 0% description coverage, so the description carries the obligation to explain it. The description doesn't explain run_id's format or role explicitly, but 'run control' clearly maps to a lifecycle/control query keyed by run. With only one parameter, the meaning is largely self-evident from the tool name and the parameter name itself (Run Id).

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 specific nouns to convey scope: 'durable lifecycle status, revision, checkpoint, cancellation, and next stage.' It clearly identifies a read/query operation on run control state. However, it doesn't explicitly distinguish it from sibling query tools like get_run, get_run_view, or get_run_events, though the specific field list ('revision', 'checkpoint', 'next stage') helps differentiate somewhat.

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 this is a status/control query tool but provides no explicit when-to-use guidance or exclusions relative to siblings. With 20+ siblings including similar query tools (get_run, get_run_view, get_run_events), there's no guidance on when to pick this one versus alternatives, leaving the agent to infer from the field names.

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