ingest_document

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

With no annotations, the description carries the full behavioral disclosure burden. It discloses that the operation persists data, that cache identity includes source SHA-256, parser configuration, OCR provider, languages, and engine versions, and that force creates an explicit new revision. This goes beyond the schema and informs the agent about side effects and revisioning, though it does not detail failure modes or permission requirements.

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 compact: three sentences total, front-loaded with the primary purpose, followed by cache identity details and force guidance. Every sentence contributes value without redundancy or filler.

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?

Given the 4-parameter complexity, no annotations, and an output schema (which removes the need to describe return values), the description is fairly complete. It covers the main behavior, cache identity, and force semantics. It omits edge cases like duplicate imports or error handling, but the provided context is sufficient for an agent to invoke the tool reasonably correctly.

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?

The schema has 0% description coverage, so the description must compensate. It explains that cache identity derives from source SHA-256 (linked to path), OCR provider (ocr_mode), and languages, and explicitly clarifies force's role for new revisions. However, it does not explain ocr_mode's enum values or the languages format (e.g., ISO codes), leaving some parameter semantics implicit. It adds meaningful guidance but not full compensation.

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 states a specific verb ('Import') and resource ('local document'), and clarifies the key action: 'persist its structured evidence'. This clearly distinguishes it from sibling tools like search_evidence, get_evidence, and render_crop, which are all retrieval or manipulation tools rather than ingestion.

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 primary use case: importing a local document once for evidence persistence, and explicitly warns that 'force' should only be used to create a new revision. It does not name alternative tools, but the contrast with retrieval-focused siblings is contextually clear. It lacks explicit 'do not use when' exclusions, but the 'once' and 'revision' guidance provides solid usage boundaries.

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