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

Annotations only declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds substantial context beyond this: the balance is a snapshot anchored to the last upstream sync rather than a live read, updateDateTime/updatedAt reflects the sync instant, credit accounts can surface BALANCE_FETCH_ERROR/BALANCE_CONSENT_ERROR as structured warnings instead of throwing, consent recovery requires reconnecting the bank, and upstream 5xx or non-Open-Finance connectors degrade to warnings. None of this contradicts the annotations; it richly supplements them.

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 dense and long, but every sentence earns its place — snapshot semantics, force_sync routing, batch limit, and two distinct error modes are all substantive. It is front-loaded with the core function before caveats. It earns a 4 rather than 5 because the error-handling material is packed into a long middle paragraph without structural separation, making it heavier to parse than necessary.

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 must convey what the agent will receive, and it sketches the row structure (updateDateTime/updatedAt, structured warnings) while fully covering the behavioral gotchas: freshness limits, batch cap, error codes, and the recovery workflow. The one gap is that the full success response shape (e.g., balance amount fields) is only implied by the tool name, not stated.

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 0%, so the description must compensate, and it does: 'Pass `account_ids` as an array (1–50)' adds a batch-size bound and per-account-id semantics that the bare schema (array of strings) does not provide. It does not describe id format or invalid-id behavior, but for a single required parameter this is meaningful compensation.

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 — 'Returns the latest available balance per account id' — and pins it to an explicit endpoint (GET /accounts/:id/balance). The snapshot qualifyer ('freshest balance the provider can serve') sharpens what the tool actually returns. It also distinguishes itself from the relevant siblings by referencing openfinance_list_transactions and openfinance_force_sync inline, so an agent can tell it apart from list/account-detail tools.

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 gives explicit routing: if a just-happened movement is missing or the balance disagrees with the sum of openfinance_list_transactions, use openfinance_force_sync and then re-read. This names the alternative tool, the exact condition that selects it, and the follow-up step, leaving nothing to inference.

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