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

Annotations already declare destructiveHint=true and openWorldHint=true, and the description goes far beyond them: timeout semantics with trackingId recovery, 409 signature-already-used meaning a duplicate went through, 403 for wrong-wallet jwt, a Linea Aave USDC funding-cap 409 that list_pools/get_balances cannot surface, and rate limits of 20/min and one call per 3s. This is exactly the kind of non-obvious failure-mode context an agent cannot get from structured fields.

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?

Despite its length, it is front-loaded with the deprecated flag, the action, and the two preconditions before any edge-case detail, and nearly every sentence carries a distinct operational fact (timeout recovery, each error code, rate limit). There is no restatement of the name or filler.

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?

With no output schema, no annotations covering the failure modes, and eight required parameters, the description carries the full burden and does: it explains prerequisites, on-chain signing scope, timeout/recovery, every documented error, and throttling. An agent can call and recover from this tool without external knowledge.

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 88%, so baseline is 3, and the description genuinely adds value beyond it: the signature's EIP-712 domain is scoped to one chain with an ERC-6492 caveat for smart-contract wallets, and jwt/signature provenance is tied to specific upstream tools. It does not add much for token/amount/deadline beyond what the property descriptions already say.

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?

"Submit a withdrawal from MetaLend's rebalancer — moves funds" gives a specific verb and resource, and the [DEPRECATED] marker plus the prepare_withdrawal prerequisite clearly separate it from prepare_withdrawal and get_withdrawal_status among the siblings.

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?

Strong routing guidance: it names the required upstream calls (submit_auth_verify for jwt, prepare_withdrawal for typedData/chain/amount/deadline) and spells out the retry-vs-escalate decision tree on timeout. The one gap: it is flagged [DEPRECATED] but never names a replacement or a condition for choosing it over a successor, so an agent has no migration path.

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