resume_plan

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

Annotations already mark readOnlyHint and idempotentHint. The description adds valuable context: it performs dependency calculation, returns a mustContinue flag, and imposes a post-call behavior requirement. No contradictions with annotations.

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 relatively concise and front-loaded with the core action. But it could be slightly more streamlined; the behavioral prohibition at the end, while important, adds length. Still, every sentence earns its place.

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?

Given the tool's complexity (reading a plan, computing dependencies, returning a mustContinue flag), the description covers the purpose, usage, and key behavioral constraints. It mentions the output components (next step, blocked steps, resumeContext) but lacks a detailed return structure since no output schema exists. It is nearly complete but could elaborate on the format of the returned data.

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 coverage is 50% (only plan_id has a description). The description adds meaning for plan_id by explaining its optionality and default behavior. However, project_root is entirely undocumented in both schema and description, so the description does not fully compensate for the coverage gap. Baseline 3 is appropriate given the partial addition.

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 verb (read, calculate), resource (Delegated Plan checkpoint from .mcp-probe-kit/plans/), and specific outputs (next executable step, blocked steps, resumeContext). It distinguishes itself from siblings like plan_heartbeat by noting it only reads state and does not execute, and contrasts with execution-oriented tools.

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 explicitly explains when to use the tool (resume a plan, both with explicit plan_id or auto-detection), what to do after invocation (must immediately execute nextStep/nextTool and call plan_heartbeat), and what not to do (prohibited from only reporting results and stopping). This provides clear guidance and alternatives by implication.

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