Triage — Reconciliation

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), so the bar is lower, yet the description adds real behavioral value: the sort order semantics, the shape of each row, the meaning of a negative cleared balance, and the cost ('costs one request') for budget-aware planning. It does not describe pagination or limits.

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-loaded with the read marker and the ordering rule, then payload details, then the rationale for staleness, then the parameter and cost note. Every sentence carries information an agent would otherwise have to guess; nothing is redundant.

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, the description needn't document return fields, and its coverage of row content, ordering, warnings, and cost is sufficient for correct invocation. The only real gap is the unexplained plan_id parameter, which matters for a tool whose output the agent must scope.

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 only partially does: stale_after_days is explained (default 45, what 'stale' means), but plan_id is left entirely unexplained despite being nullable and likely controlling scope. One of two parameters remains opaque in both schema and description.

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?

Starts with an explicit [READ] marker and a precise verb+resource statement: accounts ordered least-trustworthy-first by reconciliation staleness. It also enumerates the row payload (cleared/uncleared balances, bank-link state, warnings), so an agent can distinguish it from the other triage_* and reconcile_* siblings 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 a clear context for use ('reconciliation staleness is what decides whether the rest of a plan's numbers can be trusted') and asserts exclusive coverage ('no other tool reports it'), which implicitly steers the agent here over reconcile_preview or triage_summary. It stops short of stating explicit exclusions or naming the sibling to use for the adjacent questions.

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