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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses two behaviors the annotations cannot: that token privilege level changes what is returned (control token reveals form_url and wake_url), and that wait_seconds converts the call into a blocking wait for a change or terminal state. It also states the auth requirement (no API key, account or sign up).

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?

Four short sentences with the resource and return contents front-loaded, followed by the token-privilege and wait behaviors. The closing "No API key, no account and no sign up" is somewhat promotional in tone but does carry the auth fact, so it is not pure 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?

With no output schema and no annotations covering privileges or timing, the description does the necessary work: it names the returned fields, the conditional extra fields, and the blocking behavior. Minor gaps remain around pagination of steps/results and what a terminal run state looks like.

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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: it explains the consequence of passing a control token (extra answer links) and frames wait_seconds as waiting for a change or the end before answering rather than a plain sleep. It does not clarify the read_token-vs-control_token distinction beyond the schema's own wording.

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 opens with a specific verb and resource ("Read a run's status, steps, results and time left") and enumerates the returned facets, which cleanly separates it from siblings such as cancel_agent_run, create_agent_run and complete_agent_run_step. An agent can identify the operation without inspecting the schema.

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?

Usage is implied rather than stated: it explains that a control token additionally exposes form_url/wake_url "to hand to whoever should answer" and that wait_seconds waits for a change, which hints at the polling pattern. However, it never states when to choose this tool over read_agent_handoff, read_agent_queue_job or read_agent_inbox, and gives no when-not-to-use condition.

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