find_suspense_candidate_accounts

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

Annotations already cover the read-only, idempotent, non-destructive profile, and the description adds meaningful limits beyond them: matching is based on the structured Name field and never on any transaction's free-text description, and results are never treated as the suspense account automatically. This is useful behavioral context about false positives and confidence level.

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 compact sentences with no filler; the matching heuristic is front-loaded and the caveats follow immediately. Every clause carries information the agent needs.

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?

An output schema exists, so return-value documentation is not needed, and with zero parameters the description has no schema gaps to fill. The definition covers purpose, matching rule, and the confidence caveat, which is everything an agent needs to invoke it correctly.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies a no-argument, full-chart scan, which is consistent with the empty schema.

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 (find) and resource (chart-of-accounts rows), plus the exact matching criterion (structured Name matching placeholder-account naming like suspense, uncategorised, clearing). This distinguishes it clearly from the find_unallocated_transactions and find_broken_invoice_references siblings.

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?

Frames the output as candidates for human confirmation only, which tells the agent this is an advisory step in a workflow rather than an authoritative lookup. It does not name alternative tools or state explicit when-not conditions, so it stops short of a 5.

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