n2_mimir_lesson_propose

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

With no annotations, the description carries the full load; it does disclose two genuinely useful behavioral facts: the created object is 'dormant' and nothing is promoted automatically. However, it doesn't explain what dormant means operationally, what triggers promotion to an active lesson, or whether the operation is idempotent beyond the schema's requestId hint.

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?

Two short, front-loaded sentences with no boilerplate; the creation action leads and the lifecycle caveat follows. The second sentence is fragmentary but earns its place by conveying the non-promotion guarantee.

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?

This is a mutation tool with no annotations, no output schema, five parameters (four required), and thin parameter documentation, so the description should explain prerequisites, project/agent scoping, idempotency, and what the candidate looks like afterward. It covers only the dormant/no-promotion aspect, leaving an agent without enough to call it confidently.

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 only 20% — only requestId is documented in the schema. The description clarifies that sourceIds are 'source experience IDs', but it says nothing about project scoping, the agent field, or what the description field should contain or its limits, leaving most parameters underspecified.

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 names a specific verb and resource ('Create a dormant lesson candidate') and adds the input material ('source experience IDs'), which separates it from siblings like n2_mimir_lesson_evidence and n2_mimir_lesson_review. It stops short of explicitly naming which sibling to use for the review/evidence stages, so the differentiation is implicit rather than stated.

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?

'No automatic promotion' hints at the lesson lifecycle, but there is no explicit statement of when to call propose versus lesson_evidence, lesson_review, or lessons. The agent must infer from the name and sibling list which stage this belongs to.

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