Metis — Propose Skill Improvement

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states the proposal is queued and not directly applied, and returns a proposal ID for review. However, it does not mention any side effects, required permissions, or limits on pending proposals, which would enhance transparency for a mutation-like tool.

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 (6 lines), well-structured with a brief statement of purpose followed by Args and Returns sections. Every sentence adds value without repetition or fluff. Front-loaded with the key point about queuing and human review.

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 simplicity (3 parameters, no nested objects, output schema exists), the description adequately covers the workflow and return value. It could mention what happens after approval or rejection, or how to retrieve the proposal ID later, but it is complete enough for an AI agent to understand the proposal cycle.

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%, but the description includes an Args section that explains each parameter: agent_slug with examples, proposed_content as full replacement, and rationale with length guidance. This adds significant meaning beyond the schema's type/title, especially for rationale (schema has only default empty string).

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 'proposes' and the resource 'change to its own skill file', and distinguishes it from direct modification by explicitly referencing approve_proposal(). The title includes 'Metis — Propose Skill Improvement', further clarifying the domain and action.

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 explains that the proposal is queued for human review and not applied until approve_proposal() is called. This provides clear guidance on when to use this tool (to propose changes) and when not (for immediate effect, use approve_proposal). It references the approval step but does not explicitly compare with other sibling tools like draft_self_improvement_proposal.

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