AxKnowledgeBase_ingest_pdf_to_private_knowledge_base

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

With no annotations provided, the description fully carries the transparency burden. It discloses that the tool is synchronous and slow (takes minutes), idempotent (re-sending safe and reported as already present), and that it writes only to the private graph. These are behavioral traits beyond the schema and are clearly stated, giving the agent confidence in handling long-running or retry scenarios.

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 two paragraphs, front-loaded with the primary purpose and scope. Each sentence adds value: the first paragraph covers the action, scope, and uniqueness; the second covers runtime behavior and retry safety. There is no redundant or filler text.

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 tool with two parameters, no output schema, and no annotations, the description is remarkably complete. It explains the processing pipeline, storage, searchability, performance characteristics, and failure recovery. An agent has everything needed to invoke it correctly and understand consequences.

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 description coverage is 100% for both parameters: file_path is described as 'The absolute path to the PDF file to ingest' and doi as 'The paper's DOI, if known. Leave empty if unknown.' The description adds no additional parameter-level semantics, but since the schema already covers them, a baseline of 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?

The description states a specific verb ('Ingest'), a precise resource ('one local PDF into the organization's private knowledge graph'), and details the processing (parsed into passages, figures, tables, references) and storage. It also explicitly differentiates from siblings by being the only write tool to a knowledge graph and scoping to the private graph, leaving no ambiguity about its role.

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?

It clearly implies when to use this tool (when writing to the knowledge graph) and explains the downstream effects (reachable via search_private_knowledge_base and private_knowledge_graph_read, never via search_knowledge_base). It also advises on retry behavior after timeouts. However, it does not explicitly name alternatives or conditions for not using it, though there are no direct alternative write tools among siblings.

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