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

Annotations already declare readOnly/idempotent/non-destructive, consistent with a transaction-builder that signs outside the tool. The description adds real context the annotations lack: the capital-lock window tied to live covers and weekly settlement, and that the result is unsigned and must be signed by the wallet.

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?

Compactly front-loads the core purpose in the first clause, then packs timing constraint and signing note into two short sentences. The final clause about running from the wallet is the least clear and is slightly cryptic, but nothing is wasted.

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, the description does the necessary work of saying the return is an unsigned transaction for the wallet to sign. The lock/settlement timing covers the main behavioral risk; only the mutual exclusivity of amount vs all and the pre-check step remain slightly underspecified.

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 schema already explains amount, all, and wallet in detail. The phrase 'an amount or all: true' adds a small hint that the two are alternatives rather than cumulative, but nothing beyond that.

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?

Names a specific verb+resource ('take USDG out of the gap cover pool') and clarifies that this returns an unsigned transaction, which matters against siblings like withdraw and claim_cover. It never explicitly contrasts itself with those siblings, so an agent must infer the boundary.

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?

Provides a real usage condition – capital is locked while covers are live, from first buy of a closure until Monday's settlement, so withdraw during the week. However, it gives no guidance on when to prefer this over claim_cover, settle_cover, or plain withdraw, and 'Run from the wallet first to show what comes back' is vague enough to be ambiguous about what should be run.

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