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

With no annotations, the description carries the full burden and does notable work: prepare is free and does not compute, compute hits an authenticated API and therefore needs a credential configured first, and it warns never to invent answers or treat a continuation as authorization. It omits error behavior, rate limits, and the exact return shape, but the safety and auth profile is unusually well disclosed.

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?

Dense but efficient: the workflow comes first, readiness second, safety guardrails last, with essentially no filler. The telegraphic phrasing ('Prepare is free and does not compute') is compact rather than padded.

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 nested, no-output-schema, no-annotation tool, the description covers the dialogue flow but leaves gaps: what prepare actually returns, how the continuation object is shaped, and how errors surface. Adequate to start a call, incomplete for handling the response.

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 only 33%, so the description should compensate more than it does. It usefully clarifies that request starts empty and that answers pair with the returned questions, but it also references 'continuation.request', a field absent from the schema, which introduces ambiguity rather than resolving the nested request structure.

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 states a concrete two-phase purpose: elicit missing pricing inputs ('Ask Last Price what pricing inputs are missing') and then compute. The verb/resource are identifiable, but it never contrasts itself with the sibling compute_price, so an agent cannot tell from this text alone when to prefer one over the other.

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 explicit sequencing: start with request {}, return the questions to the caller, then send continuation.request plus answers, and switch to action compute only 'when ready'. Clear calling protocol, but it names no alternatives (e.g. compute_price, verify_price) or conditions that would rule this tool out.

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