get_evidence

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

With no annotations provided, the description carries the transparency burden. It discloses the return format (JSON payload with listed fields) and clearly indicates a read-only operation via 'Read', which implies no side effects. It does not mention error behavior or access requirements, but for a simple read tool this is reasonably transparent.

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 well-structured with a brief summary, a redundant Korean translation, and clearly labeled Args/Returns sections. The Korean duplicate adds minimal value but the overall length is appropriate and information is front-loaded. Minor redundancy prevents a 5.

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 a single parameter and an output schema, the description is complete: it explains when to use it, what input is expected, and what return fields to expect. No additional context is needed for the agent to invoke it 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 only defines chunk_id as a string with 0% description coverage, but the description compensates fully by explaining that chunk_id is the SourceChunk ID returned by query_knowledge. This provenance information is crucial for correct usage and goes well beyond the bare schema.

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: reading SourceChunk evidence for citation verification. It distinguishes itself from query_knowledge by explicitly referencing chunk IDs obtained from query_knowledge, and the verb 'Read' plus resource 'SourceChunk' make the operation unambiguous.

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 provides clear context that this tool is used for citation verification when a chunk_id is already known from query_knowledge context/citations. While it doesn't explicitly mention when not to use it, the dependency on query_knowledge output implicitly differentiates it from related tools like audit_citations.

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