incident-context

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

With no annotations provided, the description carries full burden. It mentions it returns dbt definition, test failures, and DQ checks, but does not disclose behavioral traits like read-only status, error handling (e.g., if both modelName and sourceFqn are provided), or any side effects. It provides moderate transparency but lacks detail.

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 sentences: the first defines the content, the second states the purpose. No extraneous words, every sentence earns its place. It is well-structured and front-loaded with key information.

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 4 parameters, no output schema, and no annotations, the description is somewhat incomplete. It covers the purpose and output scope but lacks details on return format, error handling, or what happens when the asset is not found. For a complex tool combining multiple data sources, more contextual information would be beneficial.

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 75% (three out of four parameters have descriptions). The description adds context by stating 'single asset deep-dive' implying modelName or sourceFqn anchors the query, but it does not explain sinceHours or extractFields. The schema already covers the purpose of the parameters, so the description adds minimal value beyond the 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 function as a single asset deep-dive combining dbt definition, recent test failures, and DQ checks. It is designed for LLM-driven incident triage, which differentiates it from sibling tools that focus on individual aspects like dbt-get-model or dq-failed-checks-by-dataset.

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 explicitly states the tool is designed for incident triage, giving context for when to use it. However, it lacks explicit guidance on when not to use it or how to choose between similar tools (e.g., dbt-get-model vs this). The phrase 'anchor an LLM-driven incident triage' implies a comprehensive investigation context.

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