av_guard

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: it auto-runs 'ensure' when no baseline exists, compares against git HEAD otherwise, caps output at a ≤3-line verdict, and offers optional HTML detail. It does not state whether the auto-ensure step mutates the workspace or what permissions are needed, which is a notable gap for a check that can create baselines.

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?

It is front-loaded with the core purpose and packed into a few dense clauses with no filler. The trade-off is density – several distinct facts (baseline logic, HEAD comparison, output format, path requirement) are compressed into a single run-on span.

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?

For a three-parameter check tool with no output schema, it covers the essentials: what it does, when to call it, how baselines are handled, and the shape of the return (≤3-line verdict). Missing only the side-effect/permission posture of the automatic ensure step.

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 all three parameters already have documentation, making 3 the baseline. The description only reiterates the required 'repo' absolute-path constraint already stated in the schema, adding no new syntax or behavioral nuance for editDir or confirmRepo.

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 names a specific capability – a daily structural acceptance check ('日常结构验收') that returns a short verdict, and notes cross-harness support (Cursor/Claude/DeepSeek). The verb+resource are identifiable, though the jargon term 'structural acceptance' is abstract enough that it doesn't cleanly separate this from siblings like av_check_layering or av_status without context.

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?

It gives clear timing guidance – 'prefer calling this before claiming completion' ('宣称完成前优先调这个') – which establishes a concrete trigger. However, it never names an alternative tool or a when-not condition, so the agent must still infer how it differs from the many av_* siblings.

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