sgraph_audit

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains what the tool returns ('JSON with cycles, hub modules, and summary metrics') and hints at heavier usage via 'occasional reviews, not daily use.' It does not explicitly state whether the tool is read-only, how expensive it may be, or what data/model prerequisites exist, so some behavioral transparency is missing.

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 well-structured, front-loaded with purpose and usage, and uses bullets and examples to make each point immediately actionable. Every sentence adds value, and there is no redundant filler.

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 description covers the main checks, aggregation semantics, and return shape, which is a solid baseline. However, it does not explain the model_id or scope_path parameters in prose, nor does it clarify how this tool relates to siblings like sgraph_security_audit or sgraph_analyze_change_impact. Given the absence of annotations and an output schema, a bit more context would be needed for fully confident invocation.

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?

The description adds meaningful context for the checks and aggregation_level parameters, going beyond the schema by explaining granularity levels with examples (2 = coarse/monorepos, 3 = default, 4+ = deeper nesting). The schema also includes descriptions for checks, model_id, scope_path, and aggregation_level, so this dimension is well covered even though the top-level parameter has no direct description.

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's function with a specific verb and resource: 'Run architectural health checks on the codebase.' It also lists the available check types ('cycles', 'hubs') and explains their meaning. It does not explicitly contrast itself with sibling tools like sgraph_security_audit, which would make the differentiation stronger.

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 clear usage context: 'For occasional reviews, not daily use.' It also gives practical guidance on aggregation_level values, including which one is good for monorepos. However, it does not explicitly say when NOT to use this tool or mention alternatives such as sgraph_security_audit for security-specific checks.

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