gograph_coupling

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

Describes tool as '100% local, read-only static analysis tool' with no side effects, no auth requirements, no rate limits. Annotations already confirm readOnlyHint, idempotentHint, and non-destructive nature; description adds valuable context about locality and restrictions.

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?

Description is well-structured with clear sections (purpose, safety, usage, completeness). Every sentence adds value, and information is front-loaded. Very efficient.

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?

Despite no output schema, description explicitly states return values (Ca, Ce, I). Provides enough context for correct usage, distinguishing from siblings without ambiguity.

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 baseline is 3. Description does not add additional parameter info beyond what schema already provides. The schema descriptions are clear, so no extra benefit from 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?

Explicitly states it assesses structural coupling and dependency ratios for Go packages. Differentiates from sibling tools like gograph_complexity by specifying package-level analysis versus single function analysis.

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?

Provides clear when-to-use ('evaluate package isolation, modularity strength, and stability indexes') and when-not-to-use ('Do NOT use for single function analysis') with an explicit alternative (gograph_complexity). Also outlines return values (Ca, Ce, I).

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