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

Beyond the annotations (readOnlyHint false, idempotentHint false), the description discloses concrete behavioral consequences: the message is persisted and execution may resume. It also specifies the three resumable states, adding real context an agent needs to predict effects.

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 sentences with no filler: the first states the primary action, the second states the side effect and its condition. The most decision-relevant information is front-loaded.

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 two-parameter tool with annotations already covering mutability, the description fully characterizes the tool's core behavior and conditional resume effect. It does not detail error handling or return value, but there is no output schema and the simplicity of the call makes that gap minor.

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 100%, and both run_id and message already have clear schema descriptions. The tool description does not add meaning beyond the schema, so the baseline score of 3 is appropriate.

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 states a concrete action—'Post a message to an agent run'—and distinguishes it from run lifecycle siblings like startRun and stopRun by focusing on message delivery. It also names the resume side effect, making the tool's purpose unambiguous.

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?

It gives explicit conditions for when the resume behavior applies ('if the run is in a resumable state (waiting, completed, or interrupted)'), which tells an agent when the tool is meaningful. It does not explicitly name alternatives, but it provides enough context to route away from unrelated run tools.

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