topai_invoice_extractor

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint and openWorldHint, so restating "read-only" and "idempotent" earns no credit. It does add "stateless" and, more usefully, enumerates the returned accounting fields, which compensates for the absent output schema. It omits failure behavior on malformed text, so it falls short of 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 sentences, front-loaded with the purpose, then usage routing, then the trait tagline. Every sentence carries information, though the trailing "read-only, idempotent" clause partly duplicates annotation data and could be trimmed.

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?

Although no output schema exists, the description compensates by listing the extracted fields; with annotations covering the safety profile and the schema covering the single input, nothing an agent needs to select or call the tool 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?

There is only one parameter and schema description coverage is 100%, with the schema itself documenting the raw-text input. The description reinforces it as "raw invoice text" but adds no format, size, or encoding detail beyond the schema. Baseline 3 is appropriate.

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?

States a specific verb (parses) and resource (unstructured invoice/receipt text) and enumerates the exact structured fields produced, so the agent knows precisely what comes out. It also names the sibling it is not (topai_math_fact_checker), making it distinguishable from the 17 other tools.

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?

Explicitly gives the trigger condition ("Use when extracting structured financial data from OCR output or raw invoice text") and an exclusion with a named alternative ("Do not use for verifying mathematical VAT calculations... use topai_math_fact_checker instead"). Both when and when-not are covered.

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