analyze_dependencies

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states 'Read-only' and explains that it returns 'live INFO.CALCDEPENDENCY lineage' plus direct dependants when an object is named. This goes beyond the schema by revealing the tool's non-mutating nature and the conditional output, though it does not address potential performance or permission aspects.

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 long, front-loaded with the action verb, and packs in the purpose, data source, conditional behavior, and read-only nature without redundancy. Every phrase earns its place, making it highly concise and well-structured.

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 no output schema, the description explicitly states what is returned (INFO.CALCDEPENDENCY lineage and, optionally, direct dependants). It also clarifies the conditional behavior based on the object parameter. The only gap is sessionId's role, but that is likely a common convention across sibling tools, so the description is complete enough for a 2-parameter read-only tool.

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 'object' parameter has a schema description, and the tool description adds behavioral context (when object is named, direct dependants are returned). However, 'sessionId' is required but lacks any description in both the schema and the tool description. With 50% schema coverage, the description only partially compensates, leaving sessionId's purpose implicit.

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 opens with a specific verb ('Analyse') and resource ('measure/column dependencies and impact'), immediately clarifying the tool's function. It further distinguishes itself from siblings by naming the exact data source (INFO.CALCDEPENDENCY) and the additional direct-dependants output, making it uniquely identifiable among many analysis-related tools.

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 implies usage for impact analysis by stating it returns lineage and dependants, but it does not explicitly specify when to choose this over alternatives like 'impact_analysis' or 'analyze_model'. No exclusions or alternative tools are mentioned, leaving the decision to the agent based on inferred context.

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