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

Annotations only state readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the description carries the burden of explaining side effects. It does this well by disclosing that the tool records exactly one adjustment row for the difference and categorizes it as outside spending, which is meaningful behavioral context beyond the annotations.

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?

Two sentences with no wasted words. The core purpose and mechanism are front-loaded, followed by usage guidance and the alternative tool, making the description quick to scan and act on.

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 simple 4-parameter tool with an output schema, the description covers purpose, mechanism, trigger condition, and the alternative. It is complete enough for most calls, though it leaves slight ambiguity around when the optional note and as_of parameters should be used.

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 50%, covering balance and as_of, but note and account_id are undocumented in the schema. The description adds useful context that the balance is 'what the bank shows' and that an adjustment row captures the difference, but it does not fully compensate for the missing parameter semantics of note and account_id.

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-resource pair ('Make an account's balance equal what the bank shows') and explains the mechanism in concrete terms: recording one adjustment row for the difference. It also distinguishes itself from the sibling reconcile_statement, giving an agent enough to tell the tools apart.

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 is explicit about when to use it: after the user reads a balance off their banking app. It also names the alternative condition, 'prefer reconcile_statement when a statement is available', which directly routes the agent to the correct sibling.

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