diagnostics

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

Discloses read-only nature, empty means clean, token-capped output, sorting order, and directory scanning limit (VTS_DIAG_DIR_MAX). No annotations provided, so description carries full burden.

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 efficiently convey purpose, format, scope, and constraints. Front-loaded with actionable 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?

Covers all key aspects: output format, scope behavior, parameter defaults, and limits. Lacks output schema but describes format adequately.

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%, but description adds meaningful context: explains scope='directory' behavior, default path resolution, backend auto-detection, and maxResults default.

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 explicitly states it returns 'compiler/linter errors + warnings' in a structured format, clearly distinguishing it from raw build output and sibling tools like 'search_text'.

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?

Describes when to use it ('compact alternative to reading raw build/compiler output') and explains scope options, but does not provide explicit when-not-to-use guidance or contrast with other diagnostic-related siblings.

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