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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with "This tool only reads" plus a routing rule to auto_match_receipts for mutation. It goes beyond annotations by documenting the per-statement row fields (period_start, period_end, opening_balance, closing_balance, book_balance_at_end, difference, agrees, document_id) and the report download link, plus an epistemic guard against over-claiming.

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 purpose, then usage triggers, then return fields — a sensible order with no filler sentences. It runs long and the closing remark about the accountant report is slightly redundant with the earlier report-link mention, but every sentence still carries information.

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?

No output schema exists, so the description carries the return-shape burden and does so field by field, plus report-format options (PDF or Excel). For a zero-required-parameter read tool with only two params, nothing an agent needs to call it or interpret results is missing.

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 coverage is 100% and both parameters are documented in the schema, including the list_companies cross-reference for company. The description only repeats that bank_account_id narrows to one account, adding no syntax or edge-case meaning beyond the schema, so the baseline 3 applies.

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+resource (reconciliation status per bank account) and enumerates the exact content returned: each statement's opening/closing balance as printed, books' balance at end date, difference, agrees flag, unreconciled counts and newest unreconciled lines. It explicitly distinguishes itself from auto_match_receipts, which does the matching.

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 concrete trigger questions ("does the bank agree?", "what was the closing balance in March?"), lists when to call it (before quoting any difference, reconciliation progress checks), and names the alternative tool for actual reconciliation with example phrasings. Also states an exclusion-style rule: never claim everything is reconciled without a result from this tool, get_attention or auto_match_receipts.

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