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

Annotations already indicate non-read-only (readOnlyHint=false), non-destructive (destructiveHint=false), and idempotent (idempotentHint=true). The description adds context by mentioning the optional idempotency key (client_request_id). However, it fails to disclose the duplicate confirmation behavior (duplicate_confirmation parameter) which is a significant behavioral trait requiring user interaction. With annotations covering the base safety profile, score 3 is appropriate for the missing duplication warning context.

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 zero wasted words. The first sentence states the core action, the second provides clear do-not-use guidance. Front-loaded and efficient.

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?

Considering the tool's complexity (8 parameters, nested objects, output schema), the description covers the main purpose and usage boundaries. It omits the duplicate confirmation flow, which is a detailed aspect. However, output schema exists to describe return values, and annotations cover base behaviors. Almost complete for a recording tool, missing only confirmation guidance.

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 75%, so the baseline is 3. The description adds value by explaining the text parameter indirectly ('natural-language text') and the overall purpose. For uncovered parameters like category_color, no additional meaning is provided. The description does not significantly enhance understanding beyond what the schema already documents.

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 verb 'Record' and the resource 'personal expense', and specifies that input is natural-language text. It explicitly excludes non-expense use cases (income, transfers, etc.) and mentions the input format, distinguishing it from sibling tools like log_transaction.

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?

Provides explicit usage boundaries: 'Expense-only: do not use for income, salary deposits, account transfers, bank credential storage, budgets, investment advice, or calendar tasks.' This tells the agent exactly when to use this tool versus alternatives.

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