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

The annotations already cover readOnlyHint=true and destructiveHint=false, so the description's job is lighter. It adds meaningful behavioral context beyond those: the merge is newest-first, status values carry lifecycle meaning (pending/processing still being read, failed could not be read), and inboxOnly returns the tray. There is no contradiction with annotations.

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 five sentences long and each sentence earns its place: overview, inboxOnly explanation, status semantics, pointer to get_receipt, and lifecycle caveat. It front-loads the core purpose first and avoids filler—a compact but high-density description.

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?

Every part an agent needs to use the tool correctly is present: return envelope, ordering, filter meanings, and the standard get_receipt pointer for deeper detail. Although it has 10 optional parameters and no output schema, the schema documents each parameter fully and the description covers the output fields and ordering, so nothing crucial is missing.

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 description coverage is 100%, so every parameter already has its semantics defined. The description reinforces q, status, and inboxOnly in slightly plainer language, but it does not go materially beyond the schema (newest-first ordering is not a parameter behavior). Baseline 3 is therefore appropriate because the schema carries the explanatory weight.

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 begins with a clear verb and resource: 'List receipt photos the household uploaded, newest first,' and enumerates the exact fields returned (merchant, date, total, tags, summary, item count, status). It also distinguishes itself from the sibling get_receipt by noting full line items are elsewhere, so an agent can tell the two apart immediately.

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 explicitly states the main use case (listing uploaded receipt photos with extracted data) and gives an alternative invocation: 'Use get_receipt for the full line items.' It also explains when the inboxOnly filter is relevant (photos not yet linked to a transaction) and how status and q operate, so no practical ambiguity remains about which tool to choose.

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