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

Annotations already declare readOnly/destructive=false, but the description adds non-obvious traits: nothing is submitted on-chain, quotes go stale in seconds, and a `quote_id` is returned for downstream consumption by execute_swap. The staleness window is a behavioral constraint no structured field conveys.

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?

Front-loaded with purpose and the quote fields, then workflow rules. Nearly every sentence is load-bearing, but the pacing is dense and mixes three topics (return fields, safety disclaimer, cross-tool workflow) in one block.

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?

Even though an output schema exists, the description flags the two most easily misread return fields (smallest unit vs UI units) and names the lifecycle handoff via quote_id. For a read-only pricing call whose safety profile is annotation-covered, nothing an agent needs to invoke it correctly is missing.

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 75%, and the description reinforces the critical unit distinction ('`output_amount` is in the token's smallest unit' vs `output_amount_ui`) and the spend/receive direction of input vs output token. It does not explain the `network` parameter, though its const value makes that self-evident.

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?

Opens with a specific verb+resource ('Price a token swap') and immediately enumerates what the price consists of (output amount, price impact, fees, slippage, minimum output). It explicitly separates itself from execute_swap ('This only prices the trade'), so an agent can distinguish it from the sibling that actually submits.

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?

Gives explicit sequencing ('Always call this before `execute_swap`'), a re-quote rule ('if they hesitate, quote again rather than executing an old one'), and a routing rule for the ambiguous case ('If `execute_swap` returns `pending` or `fill_pending`, only `get_swap_status` can tell you it completed'). Both the when and the when-not are stated.

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