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

Beyond the readOnlyHint/idempotentHint/destructiveHint annotations, the description discloses important behavioral traits: the balance is a snapshot tied to last upstream sync, not a live read; credit accounts may return specific Pluggy errors; and degraded rows carry realtime:false plus a warning rather than throwing. It states the response shape so callers know what to expect. This deeply compensates for any ambiguity the annotations do not cover.

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 one long paragraph and fairly dense, but every sentence adds distinct value: endpoint, freshness caveat, force-sync alternative, error/degradation semantics, and response shape. It is appropriately sized for the behavioral complexity, though bulleted sections or shorter sentences would improve scanability. The key freshness warning is front-loaded, which is good.

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 read-only balance tool with no output schema and a single parameter, the description covers the normal response, error rows, degraded behavior, provider-side failures, consent failures, and the refresh path. An agent has enough information to invoke it correctly, interpret the result, and take follow-up action such as forcing a sync. Nothing essential 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?

The schema has no property descriptions (0% coverage), but the description explicitly says to pass account_ids as an array and constrains the count to 1–50. It also ties the parameter to 'per account id' behavior. It does not explain whether ids are opaque strings or where they come from, but for a single-parameter tool this is largely sufficient guidance.

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 names a specific verb ('Returns'), a specific resource ('latest available balance per account id'), and the exact endpoint (GET /accounts/:id/balance), making its purpose immediately unambiguous. It also distinguishes the freshness semantics from broader account-list tools, clarifying that this is a snapshot of the upstream sync rather than a to-the-second read. This clearly differentiates it from sibling tools like openfinance_list_accounts and openfinance_list_transactions without requiring schema inspection.

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 explicitly explains when this tool is appropriate (latest available balance) and when to use an alternative: if the balance disagrees with transactions or a just-made movement is missing, run openfinance_force_sync and then re-read. It also details how errors and degraded responses should be interpreted, giving an agent clear operational guidance. This is exemplary when-to-use-vs-alternative guidance.

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