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

With no annotations at all, the description carries the full burden, and it does disclose the key async behavior: the return value is a job handle, not the status itself. However, it does not say whether asking the agent has side effects, whether the call is read-only or consumes agent work, or what errors look like for a bad session_id.

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 short sentences, front-loaded with the action and immediately followed by the runtime contract. "Without inference" is the only phrase that does not clearly earn its place, since a reader cannot resolve what it forbids.

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 tool with zero annotation coverage, no output schema, and two completely undocumented required parameters, the description is thin. It covers the job/polling contract but says nothing about the job envelope, polling cadence, session validity, or failure modes, leaving the agent under-equipped to call it correctly the first time.

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% for both required parameters, so the description must compensate and it largely does not: session_id is only hinted at by "existing agent", and request_id is never explained (presumably a job id from a prior call, but that is inferred). The agent has to guess the format or origin of both UUIDs.

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 gives a concrete verb and resource ("ask the existing agent for the current offer status") and implicitly separates this tool from get_result by noting it returns a job rather than the result. It stops short of a fully sharp distinction because the phrase "without inference" is ambiguous about whether it means no agent reasoning or no client-side interpretation.

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 explicitly routes the agent onward: the call yields a job and you should poll get_result for the outcome. It also implies a prior session/agent must exist, but it never states prerequisites, when not to use this versus get_result or start_session, or what to do if the session is unknown.

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