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

Annotations already disclose the non-read-only, non-destructive, and idempotent nature. The description adds no behavioral context beyond listing updatable fields—it doesn't explain partial-update semantics (only provided fields are modified), whether other fields are preserved, or any side effects. No contradiction with annotations, but the additional value is minimal for a mutation tool.

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 a single, efficient sentence that front-loads the action ('Correct a recorded expense') and lists fields in a natural list. No filler or redundant wording, and it stays appropriately short for the level of detail conveyed.

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 tool with 9 parameters and only 1 required, this description is too sparse. It doesn't state the update semantics (partial vs. full replacement), doesn't call out the required expense_id, and doesn't mention related_event_id or amount_usd's special rule. It also lacks any statement about when to use this vs. create_expense. An agent would need to rely heavily on the schema and inference for correct usage.

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?

With schema description coverage at only 44%, the description carries a heavier burden. It maps several parameters: 'amount' to amount, 'currency' to currency, 'date' to spent_on (ISO date), 'title' to title, 'category' to category, and 'which stop' to stay_id. However, it omits expense_id (the required field), related_event_id, and amount_usd (which has a schema description but isn't mentioned in the description). The description partially compensates but doesn't clarify all parameters.

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 ('Correct') and resource ('recorded expense'), and enumerates the editable fields: amount, currency, date, title, category, or which stop it belongs to. This clearly indicates an update operation on an existing expense, distinguishing it from create_expense. However, it doesn't explicitly differentiate from sibling update_* tools beyond resource type, though the tool name already provides that context.

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 offers no guidance on when to use this tool versus create_expense or delete_expense, nor any mention of prerequisites like requiring an existing expense_id. There is no explicit when-to-use or alternatives, and no exclusion criteria. The implied usage ('recorded expense') is present but not elaborated.

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