parse_invoice_text

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

With no annotations, the description carries the full burden; it does disclose two behavioral facts beyond the name — the operation is read-only and the response includes per-field confidence. It says nothing about what happens on unparseable or partial input, error behavior, or which fields are extracted, so significant gaps remain.

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?

A single compact clause with the action and the value-add (confidence) front-loaded; no filler. It is arguably too terse for what it omits, but nothing present is wasted.

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?

For a one-parameter extraction tool with no annotations and no output schema, the description should at least indicate return shape and failure modes. It hints at per-field confidence but not at the field set or what an empty/failed parse looks like.

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 one required string parameter with 0% schema description coverage, so the description must compensate. It implies the parameter is raw invoice text ('从非结构化文本'), which is useful, but adds no constraints on language, size, or expected encoding.

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 and resource: extract invoice elements from unstructured text, plus an output characteristic (per-field confidence). It is clearly a parsing tool, not a query tool like erp_query_invoice, though it never names that sibling or states the boundary explicitly.

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?

There is no guidance on when to use this versus erp_query_invoice, no note on input prerequisites (language, format, length), and no exclusion of cases. The parenthetical '(只读)' is the only contextual hint and it is about safety, not selection.

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