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

With no annotations, the description carries the full behavioral burden, and it does disclose two valuable traits: exports are deterministic (no inference) and are explicitly not publication or certification. It also reveals the large-payload mechanism (resumable manifest plus get_export_part). It does not state whether the call mutates state, what permissions are required, or whether repeated calls are idempotent.

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 with the primary action front-loaded, followed by the large-response escape hatch and the certification caveat. No filler; nearly every clause carries information. The only weakness is the cryptic 'without inference' phrasing, which costs a word of clarity.

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 three required params, no annotations, and no output schema, the description covers the essential mechanics (what is exported, how large results arrive, what an export does not mean). It falls short on parameter meaning, particularly how request_id relates to session_id and what each format value produces. An agent could call it, but with avoidable guesswork on the arguments.

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 three required parameters, so the description must compensate. It only loosely gestures at the format enum by enumerating exportable artifacts (offer, plan, incomplete response), without naming the format parameter or explaining the json, readable, buyer, representation, listing, and incomplete values. session_id and request_id are entirely unexplained, leaving the agent with two required UUIDs whose relationship is undocumented.

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 a specific verb and resource: exporting the session's saved offer, proposed plan, or an explicitly incomplete response, and it explicitly excludes inference. It also names the sibling used for large results (get_export_part), so the agent can distinguish it from retrieval paths. The phrase 'without inference' is somewhat obscure, but the core operation is unmistakable.

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 one concrete routing rule: when the response is large, use the resumable manifest and retrieve each indexed part with get_export_part. However, it never says when to choose this over get_result, get_status, or assess_offer_readiness, nor what conditions make an export inappropriate. Usage is implied rather than fully framed.

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