workflow

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

Description discloses a write side effect (auto-creating/updating .agents/skills/mcp-probe-kit/SKILL.md and AGENTS.md), but annotations declare readOnlyHint=true and idempotentHint=true, directly contradicting the described mutation. Per rules, score 1 and flag as annotation contradiction.

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; the first gives purpose and trigger, the second discloses the side effect. No waste, but the significant side effect could be emphasized more. Overall concise and front-loaded.

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 core purpose and the side-effect trigger, but doesn't specify the structure of the 'firstTool + phases' response. With no output schema, that's a gap. It's adequate but lacks detail on what the returned guide looks like and when the write occurs beyond 'missing'.

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?

All three parameters have solid descriptions in the schema (100% coverage), so the description doesn't need to add parameter details. It ties the 'intent' parameter to the routing behavior but provides no extra meaning beyond the schema.

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 is a fallback router that returns a phased MCP guide (firstTool + phases) based on intent. It also mentions a project setup side effect. This distinguishes it from the many task-specific sibling tools like start_feature or fix_bug.

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?

Explicitly instructs to use when unsure which MCP tool to select, giving a clear trigger condition. It does not name specific alternatives but the 'when uncertain' framing is sufficient to guide the agent away from direct task tools.

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