Summarize network errors

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

The description reveals key behaviors beyond the annotations: clustering logic (by message, type, parent), displaying worst-offending nodes, and suggesting an investigation order. Annotations (readOnlyHint, openWorldHint) are consistent, and the description adds significant behavioral context.

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?

Two sentences: the first packs the core functionality (collect, cluster, worst-offending, suggested order), and the second provides usage guidance. No extraneous content, front-loaded with 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 low complexity (2 params, optional, output schema exists), the description covers all essential aspects: what it does, how it clusters, key outputs, and when to use it. The existence of an output schema offloads return value details, so no further description is needed.

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?

With 100% schema coverage, the baseline is 3. The description adds value by explaining the group_by enum options (message, type, parent) in context, clarifying how each clustering works, which goes beyond the schema's bare enumeration.

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 collects errors across a network, clusters them by message, type, or parent container, and identifies worst-offending nodes with a suggested investigation order. It distinguishes itself from sibling tools like get_td_node_errors (which lists individual errors) by providing an aggregated, actionable summary.

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 advises using this tool instead of reading errors one-by-one, which gives clear when-to-use guidance. However, it does not explicitly state when not to use it or compare to other alternatives like document_network or get_td_node_errors.

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