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

Beyond the readOnlyHint annotation, the description explains the non-obvious behavioral distinction between LEARNED and OVERRIDE bases, what timesSeen and ruleSetOn mean, and explicitly warns not to report an override as history. This is exactly the kind of subtle behavioral context an agent needs to avoid misreporting data.

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 description is long but information-dense, and every clause contributes to understanding a genuinely complex return value. It front-loads the core purpose and then unpacks the LEARNED/OVERRIDE semantics, with the warning placed near the end for emphasis. Slightly verbose, but earned.

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 fully compensates by specifying the grouping fields, aggregates, basis values, timesSeen, ruleSetOn, and the tenant-scoped nature. It also includes the critical caveat about overrides, making the tool safely invokable and interpretable without additional context.

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?

With 0% schema description coverage, the description carries the parameter burden and delivers: counterparty is defined as a payer or payee named as printed on the statement line. This is more meaningful than the raw schema's minLength constraint, though it could add a bit more on matching or formatting expectations.

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 defines what the tool returns: historical confirmed/posted bank rows for a counterparty, grouped by category/contact/GL account, plus the live Taokeh suggestion with its basis. This distinguishes it from sibling tools like resolve_vendor or search_document_lines because it centers on precedent for categorization, not entity resolution or document search.

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?

The description states its intended use: it is the tenant-scoped precedent behind a suggestion, so an agent can explain WHY a row is categorized a certain way. It gives clear context, but does not explicitly name alternatives or state when not to use it, so it stops short of full routing guidance.

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