get_evidence

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool is 'Essential for provenance and fact-checking,' which hints at its role in verifying information, but doesn't describe key behaviors such as authentication needs (implied by 'userId' parameter), rate limits, response format, or whether it's a read-only operation. This leaves significant gaps in understanding how the tool behaves in practice.

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 and front-loaded, consisting of two sentences that directly state the tool's purpose and importance. There's no unnecessary information, and each sentence contributes value by explaining what the tool does and its context. However, it could be slightly more structured by explicitly separating usage guidance from purpose.

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 tool has an output schema (which covers return values) and high input schema coverage, the description provides a basic but incomplete context. It explains the purpose and importance but lacks details on behavioral traits, usage guidelines, and how it integrates with sibling tools. For a tool with 4 parameters and no annotations, this leaves gaps in overall completeness, though the structured data mitigates some issues.

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 input schema has 100% description coverage, clearly documenting all four parameters. The description adds some context by mentioning 'for a specific node,' which aligns with the 'for_node_id' parameter, but doesn't provide additional semantic details beyond what the schema already covers. With high schema coverage, the baseline score of 3 is appropriate as the description doesn't significantly enhance parameter understanding.

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: 'Get source signals, articles, and evidentiary depth for a specific node.' It specifies the verb ('Get') and resources ('source signals, articles, evidentiary depth'), and mentions the context ('provenance and fact-checking'). However, it doesn't explicitly differentiate this from sibling tools like 'get_node' or 'get_neighbors', which might also retrieve node-related information.

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 provides minimal usage guidance: it implies this tool is used for 'provenance and fact-checking' of a node, but doesn't specify when to use it versus alternatives like 'get_node' or 'search_graph'. There's no explicit mention of prerequisites, exclusions, or comparative contexts with sibling tools, leaving the agent to infer usage scenarios.

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