delete_expenses

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

With no annotations, the description carries the full burden of behavioral disclosure. It does add meaningful context by explaining the safety guardrail (at least one filter required) and the AND-combination behavior, which are not visible in the schema. However, it does not mention irreversibility, confirmation prompts, or what happens if the filter condition is invalid, which are relevant for a destructive operation.

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 extremely concise: two sentences, with the main action in the first sentence and the key constraints in the second. No filler or redundant wording. It is front-loaded and every sentence earns its place.

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 moderate complexity (5 optional params with filter interactions) and the presence of an output schema, the description covers the essential invocation logic: what the tool does, how filters combine, and the safety constraint. It does not explain the exact return format, but that is expected to be in the output schema. A minor gap is that it does not state what error occurs if no filters are provided, though the requirement is explicit.

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 already provides 100% coverage of parameter descriptions, but the tool description adds critical cross-parameter semantics: that all provided filters are combined using AND and that at least one is required. This goes beyond the per-field schema descriptions and clarifies how parameters interact, elevating the semantics.

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's function: 'Delete expenses matching the provided filters.' It uses a specific verb ('delete') and resource ('expenses'), and distinguishes itself from sibling tools like list_expenses and update_expenses by focusing on deletion. The AND-combination detail further clarifies its scope.

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 an important usage constraint: 'At least one filter must be provided to prevent accidental deletion of all records.' This implies the tool is for targeted deletions, and implicitly warns against calling it without filters. However, it does not explicitly contrast with alternatives or state when not to use it, so usage context is mostly implied.

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