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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the description repeats little. It adds context about the data being raw texts logged via log_transaction and grouping by bank, but doesn't detail edge cases like empty results or how the guessed bank is determined. With annotations covering safety, this is adequate.

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?

Two sentences, front-loaded with the core purpose and data, then the workflow action. No wasted words, clear and direct.

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 an output schema present, return format is covered. Complex enough to require grouping and filtering, but the description's workflow guidance is sufficient. Missing minor details like pagination or empty-state behavior, but not critical.

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 covers 50% of parameters: 'bank' has description, but 'limit' has none. The description says 'grouped by bank' which clarifies the bank filter's role, but 'limit' is left to the schema's maximum/minimum. The description partially compensates, so a 4 is appropriate.

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 clearly states the tool lists unparsed bank alerts, grouped by bank, with logged amount/merchant. It specifies the source (via log_transaction raw_text) and the purpose (to write a parse rule), distinguishing it from related tools like review_queue or parse_transaction_text.

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 when-to-use guidance: use it to write a parse rule for an unparsed bank, then test and save the rule. It implies when not to use (if you already have a rule) and names the follow-up tools (test_parse_rule, save_parse_rule).

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