dag-health-rollup

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

The description lists what the tool returns (success-rate, count breakdown, average duration, last-failed-run id, optional failing tasks). It implies a read-only operation but does not explicitly state safety or discuss side effects, auth needs, or rate limits. With no annotations, the description carries the full burden and covers main behavior adequately.

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, information-dense sentence. It front-loads the key purpose ('Aggregated DAG health') and lists outputs efficiently. Slight improvement could be splitting into two sentences, but overall concise.

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 and 4 parameters with 75% coverage, the description provides a good high-level overview of output. It does not specify exact field names or types, but the context of replacing a combo tool makes it fairly complete for the intended use case.

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% (recentRuns lacks a description). The description adds no further parameter details beyond what the schema provides. Baseline 3 is appropriate given high schema coverage but no extra param guidance.

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 provides aggregated DAG health metrics (success-rate, counts, duration, last failed run, optional failing tasks) and explicitly distinguishes it from siblings by stating it replaces the airflow-list-runs + airflow-get-task-instances combo for a health check.

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 indicates when to use: for a quick health summary ('is this DAG healthy right now?') and that it replaces a two-tool combo. It implies alternatives (the individual tools for detailed info) but does not explicitly state when not to use it. Clear context is provided.

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