Preview order

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

Adds real behavioral context beyond the annotations: it does not transact, it produces a preview_id consumed downstream, and the preview expires after 60 seconds — a time limit that materially affects agent sequencing. No contradiction with readOnlyHint=false, since the tool does create server-side state (the preview token).

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, front-loaded with the action, then the safety negation, then the output contract and its expiry. No sentence is redundant.

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?

Covers the critical facts for a preview tool with no output schema: it is non-committal, returns preview_id, and the token is time-limited. Slightly incomplete in that it doesn't say what the preview contains to read back (price, charges, validity), which the agent must discover at runtime.

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 100%, so the baseline is 3; the description goes slightly beyond by naming the returned identifier and its downstream consumer. It still says nothing about how symbol/side/quantity/order_type interact, but the schema already carries units, ranges and enum meanings.

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?

Specific verb+resource ('Check an order and get a preview') with an explicit negation of the adjacent write operation ('Does not place anything'), which cleanly separates it from place_order. An agent can pick this tool over any sibling without opening a 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?

Establishes the workflow position by stating the returned preview_id is what place_order needs, so the agent knows this is the required precursor. It doesn't spell out edge cases (e.g. what to do if the preview expires mid-flow, or when re-preview is needed), keeping it short of a full 5.

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