Promote to Mini-Skill

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds some context: mini-skills are 'permanent,' 'never decay,' and 'auto-injected at session start,' which clarifies persistence and automation. However, it doesn't cover critical aspects like permissions needed, error handling, rate limits, or what happens during promotion (e.g., if observations are removed or retained). This leaves significant gaps for a tool with multiple actions, so it's minimally viable.

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 appropriately sized and front-loaded: the first sentence clearly states the core purpose, followed by action summaries and a definition of mini-skills. Each sentence adds value without redundancy. However, it could be slightly more structured (e.g., bullet points for actions) to improve readability, but it's efficient and wastes no words.

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 complexity (6 parameters, 3 actions, no annotations, no output schema), the description is incomplete. It covers the purpose and basic behavior but lacks details on return values, error cases, or how actions interact (e.g., if 'list' shows all skills or just promoted ones). For a multi-action tool with no structured output, more context is needed to be fully helpful, so it's adequate but has clear gaps.

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?

The input schema has 100% description coverage, so the schema already documents all parameters well. The description adds minimal value beyond the schema: it mentions 'observation IDs to promote' and 'mini-skill ID to delete' in the action descriptions, but doesn't provide additional syntax, format details, or usage examples. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, as the description doesn't significantly enhance parameter understanding.

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's purpose: 'Promote observations to permanent mini-skills that never decay and are auto-injected at session start.' It specifies the verb ('promote') and resource ('observations' to 'mini-skills'), and distinguishes mini-skills as 'project-specific specialized knowledge derived from your actual memories.' However, it doesn't explicitly differentiate from sibling tools like 'memorix_skills' or 'memorix_consolidate', which might have overlapping functions, so it doesn't reach a perfect 5.

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 usage through the explanation of mini-skills as 'project-specific specialized knowledge derived from your actual memories — gotchas, decisions, fixes that generic online skills cannot provide,' suggesting it's for converting personal insights into reusable skills. However, it lacks explicit guidance on when to use this tool versus alternatives like 'memorix_skills' or 'memorix_store', and doesn't specify prerequisites or exclusions, so it's adequate but has gaps.

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