Summarize network errors

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safe read nature is known. The description adds meaningful behavior: clustering by message/type/parent, returning a summary with groups and suggestions, and indicating a severity-based investigation order. This goes beyond the annotation coverage and clarifies the tool's output behavior.

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 compact and front-loaded: it states the core function, the return shape, and the usage distinction in three sentences. Every sentence adds value, and the formatting is easy to parse.

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?

The tool has an output schema that presumably documents {total, groups[], suggestions[]}, so the description need not elaborate on return fields. It includes usage guidance and alternatives, which suffices for network-wide triage. However, it does not mention potential performance implications or whether the traversal is recursive, which could matter for large networks. Still, the provided context is strong overall.

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 coverage is 100% and both parameters ('path' and 'group_by') have clear descriptions in the schema. The description references the grouping options by enumerating 'message, type, or parent container,' but this simply mirrors the schema's enum rather than adding new meaning. It does not provide extra parameter context such as path syntax or behavior with missing paths.

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 uses a specific verb ('collect errors across a network and cluster them') and names the resource (network errors) with clear output features (worst-offending nodes, suggested investigation order). It also explicitly distinguishes itself from the sibling tool get_td_node_errors, making its purpose unambiguous.

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 provides explicit when-to-use guidance: 'Use this for network-wide triage' versus 'use get_td_node_errors when you just want the raw error list for one node or sub-tree.' This directly addresses alternatives and exclusions.

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