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

The description goes well beyond the annotations by detailing side effects: permanent and irreversible deletion, no linked-record check, ledger recomputation, and consistency of linked bills/transactions. It also includes the expectation to confirm with the user, which is behavioral guidance. This fully discloses the impact of invoking the 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 compact and information-dense, covering purpose, side effects, and usage guidance in three sentences. No redundancy or extraneous details are present. The structure is ideal for an agent to quickly grasp the tool's behavior.

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 simple delete operation with one parameter and no output schema, the description provides all necessary context: what it deletes, how it behaves (permanent, recomputes ledger), and the required user confirmation. An agent can safely and correctly invoke this tool based solely on the description, including understanding its impact on linked data.

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?

The schema has a single required parameter 'id' (string), and the description references 'by id' to indicate what the parameter is. Since the schema already fully covers the parameter definition and the description adds no additional semantic details (e.g., format, source, or validation), the baseline score of 3 is appropriate.

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 action ('Permanently delete an expense by id') and distinguishes it from other delete operations by specifying the target resource ('expense'). The scope is unambiguous, and the phrasing immediately tells an agent that this tool removes a single expense record.

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 instructs the agent to 'Confirm with the user before deleting,' which is a critical usage guideline for a destructive operation. It also notes that no linked-record check is performed and that the ledger recomputes to maintain consistency, informing the agent about when this tool is appropriate (direct deletion without collateral checks). However, it does not explicitly compare against alternative delete tools (e.g., delete_income, delete_journal_entry), leaving some inference to the agent.

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