Invoice extraction

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

The disclosure 'Costs credits from the account wallet' adds genuine beyond-annotation context about wallet consumption, which is the kind of practical behavioral trait the rubric rewards. Yet the description says nothing about failure modes, file-size limits, or behavior when multiple inputs are supplied. With annotations already covering the safety profile (destructiveHint=false), the added value earns a mid score.

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 definition is compact and every clause carries content, but the main clause is an ungrammatical fragment ('An invoice, PDF, photo, or text, into vendor, dates...') with no main verb. The useful credit-cost note is placed second, but the broken syntax undermines the overall structure.

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's field list (vendor, dates, PO refs, tax, totals, line items) is the only return-value guidance an agent receives, and it is adequate. Missing is any note about how to choose among the four optional inputs, whether they are mutually exclusive, or whether any input is required at all given that zero parameters are marked required.

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%, so all four parameters (text, fileUrl, fileBase64, fileMimeType) are already documented with descriptions. The description loosely maps accepted input types (PDF, photo, text) onto these parameters but adds no format constraints, mutual-exclusion rules, or preference guidance beyond what the schema provides.

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 title 'Invoice extraction' supplies the verb, and the description names the resource (invoices, PDFs, photos, text) and the extracted fields (vendor, dates, PO refs, tax, totals, clean line items). However, the description is a verb-less fragment — 'An invoice, PDF, photo, or text, into...' — and does nothing to distinguish this from overlapping siblings like parserail_extract, parserail_receipt, or parserail_statement.

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?

No guidance is offered for when to choose this tool over its 40+ siblings, despite obvious overlap with parserail_receipt, parserail_statement, and parserail_contract. The description only lists accepted input types; it never states exclusions, prerequisites, or alternative tool names, so an agent cannot learn selection criteria from it.

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