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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is largely covered. The description adds genuinely non-structural behavior: a fixed $0.10 per-call price and a promise that output is "small and predictable," which explains the non-read-only hint (billing) and sets expectations about result size.

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 sentences, no filler, with the output-scope claim front-loaded. The final sentence is a dangling fragment that reads as notes rather than instruction, which keeps it from a 5.

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 is the only source of return-value information, and it says only "core invoice fields" without enumerating them or indicating confidence/error behavior. The pricing disclosure is helpful, but an agent still cannot anticipate what it will receive from a paid extraction call.

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?

There is a single parameter, `document`, and schema description coverage is 100%, so the schema already does the work. The description adds no detail on expected input format (raw OCR text vs. structured text, size limits), so baseline 3 applies.

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 verb/resource pair ("return only the core invoice fields") is present, but "core fields" is never defined and the definition does nothing to separate this from close siblings such as fikra_extract_invoice, fikra_process_invoice, or fikra_extract_purchase_order. An agent can tell it extracts something invoice-related, but not precisely how it differs.

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 only usage signal is the fragment "Feeding a fixed schema into an accounting pipeline," which hints at a downstream consumer but gives no when-to-use/when-not guidance and never names an alternative among the many extraction siblings. Nothing tells an agent why it would pick this over fikra_extract_invoice.

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