get_account_changes

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

Beyond the readOnlyHint annotation, the description thoroughly discloses the return structure (changes vs. state with specific fields), the meaning of lastTransactionID, and data formats (RFC3339 timestamps, decimal strings). It also implies potential large responses when omitting the parameter. This adds substantial value beyond the annotation.

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 appropriately sized and well-structured: it opens with the main purpose, then details the return object, explains the polling pattern, and closes with data format notes. Every sentence contributes useful information without redundancy.

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?

Given the tool's complexity and the presence of an output schema, the description is complete: it specifies the output structure, the incremental polling workflow, and parameter behavior. It fully equips an agent to call the tool correctly without needing additional external context.

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 100% for the single parameter, and the schema description already explains the semantics. The description adds value by showing the exact usage pattern ('Feed the returned lastTransactionID back as since_transaction_id'), which reinforces the parameter's purpose beyond the schema.

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 the tool's function: 'Poll the configured account for state changes since a transaction.' It uses a specific verb ('poll') and identifies the resource (account state changes) and the scope (since a transaction). This distinguishes it from siblings like get_account or get_transactions_range, which provide snapshots or transaction lists.

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 operational context: it explains incremental polling by feeding lastTransactionID back as since_transaction_id, and notes that omitting it returns changes since account creation. It does not explicitly state alternatives or when not to use it, but the usage pattern is well-defined relative to the sibling tools.

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