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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds substantial behavioral context beyond annotations: the consent token requirement with 'giving:read' scope, the fact that the reader is keyed to the member and cannot be used for anyone else, the handling of refunded/charged-back gifts (counts_toward_total false), the distinction between amount_cents and gross_amount_cents, and the inclusion of anonymous gifts. It also explicitly warns against presenting the output as a tax receipt. This is rich, non-obvious behavioral disclosure.

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 longer than average, but every sentence earns its place. It front-loads the core purpose in the first sentence, then layers critical constraints (not a tax receipt, own data only, refund handling, anonymous gifts). The structure is logical: purpose → usage → exclusions → edge cases. It is not bloated; the length is justified by the sensitive financial data and the need to prevent misuse. It loses one point only because it could be tightened slightly without losing meaning.

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 financial data tool with no output schema, the description is remarkably complete. It covers what data is returned, the auth requirement, the scope limitation, the tax-receipt caveat, refund/chargeback semantics, anonymous gift handling, and the all_churches behavior. An agent has everything it needs to call the tool correctly and to avoid misrepresenting the output. The absence of an output schema is compensated by the detailed field enumeration in the first sentence.

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 schema already documents all four parameters well. The description adds meaningful context beyond the schema: it explains the consent token's scope requirement, clarifies that year is counted in each church's time zone, and explains why all_churches=true is needed for reconciling a tax year. It doesn't add syntax details, but the schema already covers those. The description's added context about the token's keying to the member and the all_churches privacy consideration earns a 4 rather than a baseline 3.

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 states a specific verb ('Fetch'), a specific resource ('the member's OWN record of what they gave in a year'), and enumerates the exact data fields returned (every gift, church, date, amount, fund, totals per currency). It also clearly distinguishes this from a tax receipt and from sibling tools like give_to_church. The scope is unambiguous: 'Their own data only.'

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 when-to-use guidance: 'Use this to help them check their records, reconcile what they think they gave, or find a gift they are looking for.' It also provides explicit when-not-to-use guidance: 'Do not use it to estimate what they can afford, compare them to anyone, suggest an amount to give, or build any kind of giving-capacity picture.' It even tells the agent to direct the member to their church for the actual tax statement, which is a clear alternative.

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