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

The description goes well beyond the annotations (destructiveHint, readOnlyHint) by detailing that it 'PERSISTED immediately,' has 'NO UNDO,' and 'Matches deterministically where it can and escalates only what it cannot confidently link.' This provides concrete behavioral insights that help the agent understand side effects and edge cases.

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 front-loaded with critical warnings ('BUSINESS-WIDE, DESTRUCTIVE, NO UNDO') and clearly organized around the three steps (dedupe, categorise, link). However, it repeats phrases like 'all PERSISTED immediately across ALL candidate entries at once' and 'There is NO single-record targeting and NO undo,' which is slightly redundant but not excessively verbose.

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?

The description provides complete context: its scope ('whole business'), its destructive nature, the actions it performs, and the caveat about deterministic matching and escalation of uncertain links. Even without an output schema, the description sufficiently informs the agent about expected behavior and potential outcomes.

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?

There are no parameters, so the schema coverage is trivially 100%. The description does not need to explain any parameter semantics, and none are missing. The absence of parameters is consistent, and the description does not imply any hidden inputs.

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's function: it reconciles the entire business's books by deduping, categorising, and linking income/expense entries to bank transactions. It explicitly says 'BUSINESS-WIDE' and 'NO single-record targeting,' distinguishing it from similar tools like match_transaction (singular) or categorize_entries, making the purpose unambiguous.

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 provides strong usage cues by highlighting that it is destructive, has no undo, and operates across all candidate entries at once. It explicitly states 'There is NO single-record targeting,' implying that for single-record operations one should use a different tool, but it does not explicitly name that alternative. This gives clear context on when to use the tool (for full reconciliation) versus alternatives.

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