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

Annotations only declare non-read-only/destructive; the description adds substantial context beyond them: refusal of balance-sheet or unclassified accounts by name with nothing saved, independence of the cost and profit dimensions, the ban on rupee amounts, and the distinction between a saved-but-not-in-force write (future effective_from, superseded_total > 0) and a live one.

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 opening sentence is well front-loaded, but the remainder is a dense single block of run-on sentences covering refusal rules, counts, and force-of-write semantics with no paragraphing, making it harder to scan than it needs to be even though most sentences carry unique 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?

With no output schema, the description carries the full burden and does so: it enumerates the returned counts (confirmed, unmapped_total, unmapped_with_balance, profit_*, superseded_total, profit_mapped_total, counts_as_of) and explains how to interpret each, including the 0-profit_centres_total edge case.

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 the baseline is 3, but the description genuinely adds semantics the schema does not: target_type selects which policy is written, the two dimensions never replace each other, and the same account may appear once per dimension per call. removal_token/removal_count are not elaborated, so not a 5.

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 first sentence names a specific verb and resource — 'Persist only the explicit account-to-centre decisions the user approved' — and the rest narrows scope to one dimension per item via target_type, distinguishing it from read-only siblings like list_account_mappings and from create_cost_centre/create_profit_centre.

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 explicit preconditions ('Before calling, show the proposal grouped by confidence tier... get a clear approval for the enumerated items') and explicit exclusions ('there is no apply-all, auto-confirm, or use-suggestions flag'), plus a when-not to repeat the call. It never names an alternative sibling tool, so it falls short of a 5.

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