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

Annotations already provide readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the description doesn't need to repeat safety behavior. It adds valuable behavioral context by specifying the output structure (list of accounts with status, balance, credit utilization, interest rate, days since last transaction) and the criteria it evaluates. This is beyond what annotations and schema (empty) provide.

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 compact and well-organized: a one-line purpose, a sentence listing attention criteria, and a 'Returns' section enumerating output fields. Every sentence earns its place, and the most important information is front-loaded. It is neither padded nor under-specified.

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 zero-parameter, read-only tool with no output schema, the description is quite complete. It specifies what the tool does, what it returns, and the criteria used. Minor omissions like whether all account types (e.g., closed accounts) are included or whether results are paginated are not critical given the tool's apparent simplicity and the absence of parameters.

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 tool has zero parameters, and the schema coverage is 100% (empty schema). The description adds the scope 'across all accounts', which is the only meaningful semantic. Baseline for zero parameters is 4; the description appropriately clarifies that no filtering is available.

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 clearly states a specific action: 'Health check across all accounts' and then details what it does: identifies accounts needing attention with concrete criteria (high credit utilization, no recent activity, approaching limits). It distinguishes itself from siblings like get_connection_health or get_financial_health_score by focusing on per-account status rather than connection health or an aggregate score.

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 provides clear context for when to use this tool: when you need a health overview of all accounts and want to locate problem accounts. However, it does not explicitly mention alternatives or exclusions, such as using get_account_details for a single account or get_financial_health_score for a single score. The usage is implied but not explicitly contrasted with siblings.

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