review_unapproved

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

Beyond the readOnlyHint=true annotation, the description adds significant behavioral context: it details the 'flags' array, explains that match_broken is read-only via API but the transaction is mutable, and warns against approving uncategorized transactions. No contradiction with 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?

The description is front-loaded with the core purpose, and detailed flag explanations are provided after. It is somewhat verbose but well-structured, with each part serving a purpose. A slightly more concise version could be considered.

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 lack of output schema, the description explains the grouping and the flags array, and mentions the summary format. It covers the main aspects but could be more explicit about the exact response structure.

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% with good parameter descriptions, but the description adds value by explaining the default behavior of budgetId and the use case for summary=true, including the effect on the response.

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 retrieves all unapproved transactions grouped by status (ready to approve vs needs category first), and it distinguishes this from siblings by focusing on unapproved transactions, which no other sibling tool does.

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 the tool (reviewing unapproved transactions) and includes a strong guideline not to approve uncategorized transactions without explicit user instruction. However, it does not explicitly name alternative tools or state when not to use this tool.

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