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

Annotations already declare readOnlyHint, destruptiveHint false and openWorldHint false, so safety is covered; the description adds genuinely new behavior: cursor-based pagination, long-polling via waitMs, and a pendingQuestion state that requires a follow-up call. It doesn't state what a waitMs timeout returns or how errors surface, which keeps it below 5.

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?

Three short sentences, zero filler, and the core read purpose is front-loaded before the parameter hints and the follow-up routing. Every sentence carries actionable information.

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 no output schema, the description must sketch the return surface, and it does: status, messages, events, and the pendingQuestion signal. Combined with annotations covering the read-only safety profile, an agent has enough to call this correctly; only timeout/error semantics are absent.

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 0%, so the description must carry the load and largely does: afterRev is explained as a cursor taken from the prior response, and waitMs as a blocking wait for new messages. runId is left implicit, though its meaning is evident from the tool name and required status.

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 with scope: 'Read one agent run: status and its messages and events.' The word 'one' implicitly separates it from the list variant, and 'messages and events' tells the agent what payload to expect. It stops short of explicitly naming agent_run_list as the alternative, so a 4 rather than a 5.

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 concrete operational guidance for two of three parameters: pass afterRev from the last response for the next page, set waitMs to wait for new messages. It also routes the agent forward with 'If pendingQuestion appears, answer it with agent_run_message,' which is an explicit alternative-tool handoff. What's missing is when to choose this over agent_run_list.

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