ksef_extract_invoice_source

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds that it uses a local LLM, which is a key behavioral trait. However, it does not disclose potential latency, model availability, or that results may vary, which are relevant for a tool dependent on local inference.

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 description is a single, well-formed sentence of 14 words that efficiently conveys purpose, mechanism, and constraint without redundancy.

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?

Despite strong annotations, the description omits prerequisites (e.g., source documents must exist), output details (output schema exists but not referenced), and parameter interdependencies. For a tool with 4 parameters and a local LLM dependency, this is insufficient for reliable agent use.

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?

With 0% schema description coverage, the description must explain parameters but does not mention any. While names like 'source_document_ids' are suggestive, 'draft_id', 'target_fields', and 'max_candidates' lack explanation of their roles and interactions, leaving the agent to guess.

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 description clearly states the tool uses a local LLM to propose source-backed invoice fields without mutating drafts, providing a specific verb (propose) and resource (invoice fields from sources). It distinguishes from siblings by emphasizing non-mutation, though it could explicitly contrast with similar advisory tools like ksef_advise_vat_treatment.

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 description implies the tool is for proposing fields before mutation but does not explicitly state when to use it over alternatives like ksef_update_invoice_draft or ksef_advise_vat_treatment. Given the sibling list, more guidance on appropriate contexts would be helpful.

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