list_recent_plans

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

Discloses that the data is in-memory and clears on server restart (transient nature). Does not claim side effects, and the return format is fully specified. No annotations exist to carry burden.

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?

Bilingual but still concise with only three sentences plus return format. One redundant translation can be excused for inclusivity.

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 no parameters and no output schema, the description fully specifies return structure and behavioral traits (in-memory, clears on restart). Complete for its complexity.

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?

No parameters in schema, so no additional info needed. The description is complete for zero-parameter tool.

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 it returns plans recorded in the current session for debugging. It specifies the four types of plans (assembly plans, feature plans, batch jobs, macro jobs) and distinguishes itself from sibling record/run tools as a retrieval tool.

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 says 'useful when LLM forgets a plan ID' providing clear usage context. While it doesn't explicitly list when not to use, the debug-aid framing and sibling tool set provide sufficient guidance.

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