Triage — Uncategorized

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

Annotations already cover the safety profile (readOnly, non-destructive), and the description adds substantial behavioral detail beyond them: the two automatic exclusion classes and why, the meaning of count vs raw_count vs excluded, and the fact that count/raw_count describe the whole queue regardless of paging. That is exactly the extra context annotations cannot carry.

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?

Front-loads the purpose and exclusion rules before the flag and paging details, so the critical routing information comes first. The '533 into 14' anecdote is illustrative of filtering impact but is the one sentence closest to filler.

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 structure needn't be spelled out, and the description still explains the key derived fields (count, raw_count, excluded) that an agent needs to interpret results. For a 5-param, zero-required read tool this is complete.

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 description coverage is 0%, so the description must compensate, and it explains four of five parameters: limit/offset paging semantics (with the non-obvious note that counts ignore paging), and include_transfers/include_tracking_accounts. Only plan_id is left undocumented, which is a minor gap given its obvious meaning.

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 and resource ('Transactions that genuinely need a category') and immediately qualifies the scope with the two exclusion rules, which is exactly what separates it from sibling triage tools like triage_unapproved or triage_pending_imports. An agent can tell what queue this returns without opening the schema.

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 clear context for when to reach for it (finding categorizable work) and explicitly describes the default exclusions plus the flags (include_tracking_accounts, include_transfers) that reverse them. It does not name alternative siblings such as bookkeeping_categorization_suggestions, so routing among triage/bookkeeping tools is left partly to inference.

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