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

Annotations already declare read-only, idempotent, non-destructive, so the behavioral bar is lower; the description still adds real value by disclosing the return payload (sign_url), its 15-minute lifetime, automatic re-quoting when stale, and an explicit security instruction not to have the user paste transaction data. The 'gets a new quote itself when the price is out of date' line is slightly confusing for a revoke flow and reads like boilerplate, which keeps it short of a 5.

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?

The core purpose is front-loaded in the first sentence and the operational guidance follows in a logical order. The passage is somewhat long and includes one tangential sentence about price re-quoting that does little work for a revocation tool.

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 carries the return-value burden and does it by identifying sign_url, its expiry, and the signing workflow. It is nearly complete for a three-parameter builder, missing only a fuller picture of the returned object (e.g. whether transaction data is also returned).

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 100%, so token, wallet, and spender are all documented already; the description only reinforces relational meaning (wallet is the approval giver that signs, spender is who loses access). It adds no format, validation, or edge-case detail beyond the schema, so baseline 3 applies.

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 precise verb and resource — build an unsigned transaction that resets a token approval to zero — and explains the effect (the spender can no longer move the token). It also separates itself from the rest of the family by noting that no keyfo tool performs the signing step, so an agent knows this is a build-only tool.

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?

Tells the agent what to do with the result: show the sign_url to the user and never ask them to paste transaction data, plus the constraint that a key is required and that signing happens outside keyfo. It stops short of naming a specific alternative to use instead (e.g. reading approvals first via stock_approvals, which is only referenced in the schema), so it gives clear context but no explicit when-not rules.

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