discover_sources

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

The description discloses key behavioral aspects: it returns unified AssetRef results, preserves canonical format for short evidence spans, and provides only a discovery-only preview for long spans, with the caveat that full verifiable AssetRef must be obtained from persisted citations or the agent-asset bundle. This gives the user a clear expectation of output behavior.

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 concise, consisting of two clear sentences that efficiently convey the tool's function and output behavior. It is well-structured and easy to read, with no redundant or verbose wording.

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?

While the description covers the output format and handling of spans, it omits essential context about how to invoke the tool correctly, particularly regarding the parameters. It also does not mention the expected return structure in detail beyond the AssetRef format, leaving gaps for a user who needs to understand the full context of usage.

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 description provides no explanation of the parameters (query, doc_ids, include_kg, limit) and the schema also lacks descriptions. With 0% schema coverage, the description completely fails to compensate, leaving the user without any understanding of what these parameters do or how to use them.

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's purpose: to search for data sources across documents, integrating multiple databases (Section, Figure, Table, Knowledge Graph) and returning a unified AssetRef format. This distinguishes it from sibling tools like get_docx_content or parse_pdf_structure, which are more specific to content extraction.

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 does not provide explicit guidance on when to use this tool versus alternatives, such as what scenarios warrant discover_sources instead of find_evidence_spans. It also lacks any mention of prerequisites, limitations, or contexts in which it should not be used.

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