Reconcile Bank Transactions

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

The description aligns with the destructiveHint=true annotation by describing execute modes that modify data. It adds context about blocking behavior and flagging, but doesn't fully detail what gets created or destroyed (e.g., journals, transactions). Still, it is more informative than the bare annotation.

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 a single long sentence (82 words) that conveys all modes and their conditions. While front-loaded with the purpose, it could be more scannable as a list. However, it remains efficient and avoids redundancy.

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?

Given no output schema, the description does not mention return values (e.g., suggestions, plan handles, execution results). For a complex multi-mode tool, this is a gap. It covers usage well but misses post-invocation behavior.

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 100% schema coverage, the description adds value by linking parameters to specific modes (e.g., plan_handle required for execute modes, block_on_duplicate for invoice-matching). This context helps the agent understand parameter relevance beyond schema definitions.

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 identifies the tool as a 'Merged bank reconciliation entry point' and lists distinct modes (suggest, dry_run_auto_confirm, etc.), each with specific purposes. It differentiates from siblings like reconcile_inter_account_transfers by being a unified entry for multiple reconciliation workflows.

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?

Explicit guidance is provided for each mode: 'use mode='suggest' for invoice-match suggestions', and notes that execute_inter_account requires plan_handle from the dry run. This tells the AI exactly when and how to use each mode.

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