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

Annotations already declare idempotentHint=true, but the description earns credit by explaining the mechanism: the caller must supply its own UUID as id so that a repeat call is a no-op. That operational detail is not derivable from the annotation alone. It still omits auth/permission requirements and what the call returns.

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?

Five compact sentences, front-loaded with purpose and then ordered by importance: idempotency, argument requirements, amount units, date formats. Almost every sentence earns its place, though the trailing 'month is a budget period YYYY-MM' clause is irrelevant to this tool's schema and adds noise.

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 13-parameter mutation tool with no output schema and no field-level schema descriptions, the description covers the critical semantics but leaves the multi-currency transfer fields (toAmount, toCurrency, baseAmount) and currency/isRefund/note unexplained. Adequate for a simple expense call, but incomplete for the transfer and multi-currency cases the tool explicitly supports.

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 0%, so the description carries the full burden, and it compensates well for the highest-risk fields: amount unit convention (integer minor units, 45000 = 450.00), the idempotency key id, conditional categoryId/toAccountId, and the YYYY-MM-DD date format. However, roughly half the parameters (note, currency, isRefund, toAmount, baseAmount, toCurrency) remain undocumented, and the stray 'YYYY-MM budget period' remark has no corresponding schema parameter, which is mildly confusing.

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?

States a specific verb and resource ('Add an expense, income or transfer') and enumerates the three record types the tool accepts, which immediately distinguishes it from update_transaction, bulk_update_transactions and delete_transaction. An agent can identify the tool without opening the schema.

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?

Gives explicit conditional requirements that guide invocation: categoryId is required for expenses and income, transfers need toAccountId, and it routes to list_categories to obtain a categoryId. It does not explicitly contrast with update_transaction or bulk_update_transactions, but the conditional argument rules provide clear usage context.

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