ingest_financial_document

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

No annotations are provided, so description must carry behavioral disclosure. It states the core action and side effect ('stages them for graph ingestion') but lacks details on idempotency, error handling, or permissions. Adequate but not comprehensive.

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?

Single sentence, 12 words, front-loaded key information. Very concise, but could benefit from slight expansion to cover usage context or parameter hints without losing efficiency.

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?

Tool has three required params, no output schema, and no annotations. Description is too brief to cover return values, error scenarios, or integration with sibling tools. Incomplete for a production-grade agent.

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 only 33% (only file_ref has a description). Description does not explain user_id or document_type beyond what enums or schema provide. Fails to compensate for low coverage, leaving the agent guessing about parameter meanings.

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?

Description clearly states verb ('parses'), resource ('uploaded PDF'), and result ('structured JSON entities staged for graph ingestion'). Distinguishes from sibling tools that are for retrieval, analytics, or graph manipulation. No ambiguity.

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?

Implies usage for ingesting new documents before graph ingestion, but does not explicitly state when to use this tool versus alternatives like fetch_account_summary or upsert_graph_node. Could be improved with contextual cues.

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