run_audit

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

Annotations already declare it read-only, idempotent and non-destructive, so the safety bar is low. The description still adds genuine behavior beyond that: output streams live to server logs, it requires network access to a live VB backend, and failures surface a plain-language hint. It doesn't say what the audit actually checks, but the disclosure is above the annotated baseline.

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?

Three tight sentences, front-loaded with the action and followed by operational preconditions. Every sentence carries content; nothing is padding, though the failure-hint detail is slightly incidental.

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?

With no output schema, the description compensates by noting that output streams live to server logs and that errors include a plain-language hint, covering both the success and failure paths. Missing only what the audit checks and how a caller observes results from logs.

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 100%, so both repo and appName already carry full detail (defaults, list_repos/list_apps pointers). The description adds only the phrase 'for a VBCS app' and no format or syntax beyond the schema, so the baseline 3 applies.

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?

States a specific verb (run) and resource (grunt-vb-audit) scoped to a VBCS app, which separates it from run_build and the vbstudio_* build tools. It does not explicitly say how it differs from audit_service_calls, but the audit-vs-build distinction is inferable.

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 points at a prerequisite ('needs the same setup as run_build') and an environmental condition (network access to a live Visual Builder backend), which is useful. However, it never states when to choose this tool over run_build or audit_service_calls, so usage is only implied.

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