draft_self_improvement_proposal

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

The description discloses the main behaviors: reads themed reflexions, appends to skill.md, queues proposal as draft. It explicitly notes the draft is not applied. However, it is slightly ambiguous whether the append to skill.md is a permanent modification or a temporary step, as it later says the result is queued. Without annotations, this is mostly transparent but could be clearer.

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 concise with three sentences, front-loading the purpose. It uses backticks for code terms. The mention of 'Phase 9b' adds minor jargon, but overall efficient and well-structured.

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 steps (reading reflexions, appending to skill.md, queuing proposal) and the draft status. With an output schema presumably present, the return value need not be detailed. However, it lacks details on the lifecycle of skill.md modification and the exact format of the proposal. Still, it is largely complete for a draft operation tool.

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?

With 0% schema description coverage, the description must explain parameters. It only explains agent_slug ('Reads themed reflexions for agent_slug'). The 'days' parameter is not mentioned, despite having a default of 14 and likely controlling the time window for reflexions. This leaves a gap in understanding how to use the tool effectively.

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 action 'Draft a skill-improvement proposal from recent reflexions' and distinguishes it from the sibling tool apply_proposal by stating 'The draft is NOT applied. Use apply_proposal(id) to write it to disk.' The verb 'draft' and resource 'skill-improvement proposal' are specific and unambiguous.

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 states when not to use this tool ('The draft is NOT applied') and directs the agent to an alternative ('Use apply_proposal(id) to write it to disk'). This provides clear decision support for tool selection.

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