draft_self_improvement_proposal_tool

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

No annotations are provided, so the description carries the full burden. It describes reading reflexions, appending to skill.md, and queuing as draft, and explicitly states the draft is not applied. However, it does not mention side effects (e.g., whether it overwrites existing drafts), permissions, or error handling. The transparency is adequate but not exhaustive.

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 multi-sentence but well-structured: it starts with the main purpose, then details the actions, and ends with a clarification about not being applied. It is concise without extraneous words, though one or two sentences could be slightly tightened.

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 tool has 2 parameters and no annotations, and there is an output schema (not shown) which presumably covers return values. The description covers the main workflow but misses potential prerequisites or error conditions (e.g., what happens if no recent reflexions exist). It is reasonably complete for a straightforward drafting 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?

Schema description coverage is 0%, so the description must compensate. It mentions agent_slug in the context of reading reflexions, but the 'days' parameter (default 14) is only vaguely implied by 'recent reflexions' and not explicitly described. The description adds some meaning but leaves the role of 'days' unclear.

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 drafts a skill-improvement proposal from recent reflexions, naming the phase (9b), the input (agent_slug), and the actions (appends a section, queues result). It explicitly distinguishes from the sibling 'apply_proposal_tool' by stating the draft is not applied.

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 implies when to use (when drafting a proposal from recent reflexions) and suggests an alternative ('use apply_proposal(id) to write it to disk'). However, it does not explicitly specify scenarios where drafting would be inappropriate, such as if a draft already exists.

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