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

With no annotations, the description carries the full burden and does disclose meaningful behavior: it produces signed attestations, issues verdicts, and constrains tolerance to a fixed 50 bps band. It does not disclose authorization requirements, whether the handle is single-use or idempotent, whether state persists on the server, or failure modes, which matter for a signing/certification call.

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 sentences, front-loaded with the core action, then usage constraints, then return payload. The return-value enumeration is dense but every item is load-bearing given there is no output schema, and 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?

Given 10 params, a nested object, no annotations, and no output schema, the description compensates well by enumerating the returned identifiers, hashes, asset ids, rate, band, verdicts, and attestations. The remaining gap is operational: no explanation of the action enum semantics, the optional provider/protocol inputs, or how verdicts should be interpreted.

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?

It adds real meaning for a few inputs: asset fields are returned as CAIP-19 ids and max_slippage_bps is described as a pre-committed tolerance fixed at 50, beyond the schema's const. But at 50% schema coverage with 10 params, it leaves the action enum, amount_usd, providers, protocol_id, source_group_count, and the nested decision_input quote shape essentially undocumented.

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?

The description names a specific action and resource: certify a swap/DeFi intent and open a verifiable pre-trade evidence handle. It also states what the tool is NOT ("not trade authorization") and positions it temporally before execution, which separates it from prepare_swap and issue_execution_receipt in the sibling set.

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?

It gives explicit trigger conditions ("when a principal needs a signed pre-trade handle to bind an execution receipt later") and explicit exclusions ("do not use it as trade authorization and do not call it after the trade"). It stops short of naming a concrete alternative sibling such as check_trade_safety for safety checks or issue_execution_receipt for the post-trade step, leaving that mapping implicit.

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