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

Annotations declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, yet the description adds the crucial boundary "No signing or broadcast," clarifying why a non-read-only hint still means no irreversible on-chain action. It also adds a genuine safety caveat ("a source burn is never proof of destination delivery") that no annotation 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?

Three tight lines, front-loaded with purpose, then the step list, then a caution — no filler. Minor friction from terminology drift: the description says "route ID" while the schema calls the field transfer_id, which costs a little clarity in an otherwise efficient 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?

For a multi-step, no-output-schema tool, the description covers purpose, the step vocabulary, the no-sign/no-broadcast boundary, and a safety invariant — enough for an agent to sequence calls correctly. It omits per-step requirements (e.g., what each step returns or needs), but annotations and the step list fill most of that gap.

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 0%, so the description must compensate, and it does the most important part: it enumerates the valid step values (which the schema leaves as an unconstrained string) and explains that burn/mint consume source/destination hashes, mapping to the transaction parameter. transfer_id itself is only obliquely referenced as "route ID," leaving a small gap.

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?

States a specific resource (an existing CCTP transfer) and the operations it supports (inspect/prepare/reconcile), which clearly separates it from the read-only quote step. It does not explicitly name the sibling quote_usdc_cross_chain_transfer, so an agent must infer the boundary, but the "existing transfer" framing makes the distinction largely self-evident.

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?

The description lays out the full step sequence (status, prepare-burn, burn, attestation, prepare-mint, mint), which conveys workflow context well. However it never states when to reach for this over quote_usdc_cross_chain_transfer or the prepare_* siblings, and gives no prerequisites or ordering rules, leaving usage to inference.

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