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

Annotations already cover readOnly/idempotent/non-destructive, but the description adds material facts beyond them: the code is read-only and expires, results are summarized, and it details what argument data is stored versus hashed or excluded. The tail about exit tools logging counts is tangential to this tool, which slightly dilutes the transparency payoff.

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 precondition and the return summary are front-loaded, which is good. However, a large block of privacy/data-retention text and a sentence about exit tools inflate the description well beyond what an agent needs to select and call this 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?

There is no output schema, so the description carries the burden of describing returns – and it does so thoroughly (verdict, proven saving, proof, steps, checks) while also stating the entry precondition and post-call workflow. Nothing essential for correct invocation is missing.

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% and the single 'code' param is already documented with an example, so baseline is 3. The description adds useful provenance the schema lacks: where the code comes from, that it starts with sca_, and that it expires.

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 verb+resource ('Returns their own savings plan') and enumerates exactly what comes back: subscriptions, verdict, proven saving, proof, steps and checks. It distinguishes the tool's scope from query/audit siblings implicitly, but never names an alternative like get_exit_plan or audit_stack, so the differentiation is not explicit.

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?

Gives a clear precondition: use only when the user supplies a Stackcut agent code beginning with sca_, copied from 'Send to my agent'. It also prescribes workflow ('walk them through from the biggest proven saving down and ask before any cancel, purchase or sign-up'). It stops short of naming when-not-to-use or which sibling to pick instead.

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