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

Adds substantial context beyond the annotations: the run is non-destructive to the source files ('Does not change any file'), it writes new Excel and PDF artifacts to the plugin server with private links that expire after one hour, and it discloses scale limits (20,000 rows per file; 2,000,000 cells for CSV/text). This also explains why readOnlyHint=false despite no mutation of user data, so there is no contradiction with the annotations.

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 'Use this when...' trigger and example utterances, then flows into behavior, limits, and side effects. It is one dense run-on paragraph and a few clauses could be split, but nearly every sentence carries information an agent would otherwise have to guess.

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?

For a 12-parameter, nested-object tool with an output schema, the description covers the missing pieces: what the analysis does, what artifacts come back ('the same Excel and PDF downloads'), retention and privacy of those downloads, and explicit failure boundaries. An agent can decide to call it and predict the effects without opening the schema.

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 100%, so every parameter, including the sign, date-order, and column-mapping objects, is already documented in the schema. The description adds only a little interpretive detail (the up-to-4 item set maps loosely to max_group_size, and 'divisible by 9' explains the transposition check), so the baseline of 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?

Names a specific verb and resource (explain why the bank reconciliation is off) and spells out the mechanics: rerun the matching, compute adjusted bank vs adjusted book balances, and isolate the smallest set of items (up to 4) that explains the difference. It implicitly ties itself to the sibling reconcile_bank_to_books ('Runs the same matching') but never states plainly that the sibling performs the reconciliation while this one only diagnoses the gap.

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 concrete trigger condition (user attaches bank and books files, supplies both ending balances, and asks why the reconciliation does not balance) along with literal user phrasings. It also states what the tool cannot do (find items missing from both files) and its row/cell limits, but does not say when to reach for reconcile_bank_to_books instead.

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