attach_file_to_transaction

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

The description discloses important behavioral details beyond the minimal annotations: reads from the host's local filesystem, determines type by content, rejects non-image/PDF files, enforces a 10MB limit, and honors the LUNCHMONEY_ATTACHMENTS_DIR restriction. This goes beyond what the idempotentHint: false annotation conveys and prepares the agent for validation errors and environment-specific behavior.

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 three sentences with no wasted words. The first sentence states the core purpose, the second lists allowed types, and the third covers constraints (filesystem, content detection, and directory restriction). Every sentence contributes valuable information.

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?

The description thoroughly covers the tool's constraints and environmental dependencies. However, since there is no output schema, it would be beneficial to state what the tool returns upon success (e.g., an attachment object or ID). Despite this minor gap, the description is sufficient for an agent to select and invoke the tool correctly.

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 descriptions cover all four parameters fully, but the tool description adds extra meaning not present in the schema: the 10MB capacity constraint and the rule that the type is determined from actual contents (which affects file_path and content_type semantics). This provides useful selection and invocation context beyond the schema.

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 uses a specific verb ('Attach') and clearly identifies the resource ('a local image or PDF receipt to a transaction'). It is unambiguous and easily distinguishes this tool from siblings like 'get_transaction_attachment_url' and 'delete_transaction_attachment' based on the action it performs.

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 implies usage for attaching receipts but does not explicitly state when to use this tool over alternatives or provide exclusions. Sibling tools for getting/deleting attachments exist, but the description does not mention them or give conditions for choosing this tool, so guidance is only implied.

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