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

Annotations already disclose that this is not read-only and not idempotent, so the agent knows a mutating, chargeable call is involved. The description adds the one thing annotations cannot carry: a fixed price of $0.15 per call, which matters for a billing-sensitive flow. It omits practical behaviour such as input size limits or what happens on an unparseable receipt, keeping it below a 5.

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?

Three short fragments, front-loaded with the highest-value information (what gets extracted). The final fragment is a dangling noun phrase with no verb, which is slightly wasteful, but nothing is padded or repetitive.

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?

With no output schema, the description correctly compensates by enumerating the extracted fields, and it discloses the per-call cost. For a single-parameter text-in tool that is nearly sufficient; only edge-case behaviour (multi-receipt input, unparseable documents) is unstated.

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 coverage is 100% on the single 'document' parameter, so the schema already explains that it takes document text. The description adds nothing about the parameter — the merchant/date/total list describes the return payload, not the input. Baseline 3 applies where the schema does the work.

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?

A specific verb plus resource plus explicit output fields: 'Extract merchant, date, total, tax and items from a receipt.' An agent knows exactly what it gets back. It does not, however, distinguish itself from near-neighbours such as fikra_get_receipt or fikra_extract_invoice_fields, so the sibling differentiation is left implicit.

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 trailing fragment 'Logging expenses from receipts without manual entry' implies the use case (expense capture) but reads as a marketing line rather than guidance. No when-not conditions and no named alternative such as fikra_get_receipt or fikra_reconcile_invoice_receipt, so the routing decision is left to inference.

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