Deep research with Ledger AI

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, which inform the AI that the tool is safe, idempotent, and non-destructive. The description adds only that it uses 'research orchestration' and returns citations/context, which is useful but does not significantly expand on behavioral traits like potential latency or error conditions.

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 a single sentence, efficiently stating the action and output. It is front-loaded with the verb 'Run'. However, it lacks structural elements like bullet points or separate sections that could improve scanability, though it remains concise and to the point.

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?

An output schema exists (not shown), but the description does not mention any additional context such as expected response time, cost implications, or whether the tool can handle follow-up questions. The phrase 'with citations and context' is somewhat vague. Given the tool's apparent complexity, the description could provide more complete guidance for the AI.

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 0% for the single parameter 'question'. The description merely states that a question is passed, offering no additional meaning, format, or examples to compensate for the lack of schema documentation. The AI receives no guidance on what constitutes a well-formed question.

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 verb 'Run a question through' and the resource 'TNL Ledger AI research orchestration', and specifies the output 'answer with citations and context'. This differentiates it from sibling tools like tnl_latest_news or tnl_asset_intelligence, which are narrower in scope.

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?

No explicit guidance on when to use this tool versus its siblings (e.g., tnl_latest_news, tnl_search_news). There is no mention of prerequisites, exclusions, or alternative tools for specific use cases, leaving the AI to infer usage context.

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