manage_account

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently warns that delete permanently deletes the account and that transactions are 'NOT deleted by default,' and it notes that synced accounts are read-only. These are important behavioral traits beyond what the schema conveys. It does not mention permissions, rate limits, or response formats, but the destructive warning and read-only constraint add significant transparency.

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 well-structured and efficient. It opens with a one-sentence summary, then provides a clear action-by-action breakdown in distinct lines. Every sentence adds value: the warning about delete is critical, and the optional parameters are listed without unnecessary elaboration. No filler or redundancy.

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 10 parameters and 3 actions, the description covers the essential context: what each action does, required vs. optional fields, and a critical warning for delete. It does not describe return values, but with no output schema that is not a major gap. It could mention the response format or potential errors, but the description is sufficiently complete for an agent to safely select and invoke the tool.

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 has 100% coverage, but the description adds action-specific semantics: it explains which parameters are required for create (name, type, balance) and which are optional, and clarifies that update accepts 'any fields to change' while delete only needs id. This goes beyond the schema's per-field descriptions by grouping parameters by action, making the tool easier to invoke correctly.

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 purpose: 'Create, update, or delete a manual Lunch Money account.' This specifies the verb (create/update/delete), resource (manual accounts), and scope (Lunch Money), and distinguishes it from siblings like get_accounts (which reads accounts). The additional note about synced (Plaid) accounts being read-only further clarifies the boundary.

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 clear context for when to use the tool: it is for manual accounts, and synced (Plaid) accounts are read-only, which serves as an explicit exclusion. The per-action breakdown (create/update/delete) with required parameters gives practical usage guidance. However, it does not explicitly name alternatives (e.g., get_accounts for viewing), though this is implied by the sibling tool names.

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