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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered and the trailing 'Read-only' restates it. The description's real contribution is the behavioral contract of the result: three named states with their meanings and what each implies about progress, which is essential since there is no output schema. It could still say how often the state changes or whether polling is expected.

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 front-loaded sentence with the state machine laid out in the order an agent will encounter it, and the parentheticals each add meaning. The closing 'Read-only.' is dead weight because the annotation already declares readOnlyHint and it isn't part of the state enumeration.

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 zero parameters, no output schema, and full annotation coverage, the description carries the main remaining burden, the shape of the response, and it does so by defining all three states plus the action each implies. It is essentially complete for a status-polling tool; only polling cadence or the exact returned field names 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the schema is trivially complete. A baseline of 4 applies for a no-argument tool.

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 the resource (the setup test) and its purpose (reporting where the test currently stands), then enumerates the three concrete states: waiting, received, replied. An agent can distinguish this from start_setup_test by the fact that this only reports status. It stops short of a crisp verb-and-resource opener, but the state enumeration makes the intent 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 actionable next-step guidance for the 'received' state: read the brief, find the chat, and answer it with reply_in_chat, which routes the agent into the follow-on workflow. What's missing is explicit sequencing ('call this after start_setup_test') and a statement of what to do if the state is 'waiting'. Guidance is present and useful, but not a full when/when-not rule set.

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