n2_mimir_lesson_review

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

With no annotations, the description carries the full burden, and it does disclose real behavior: hold/retire retain history, supersession is atomic, and no executable rules are created. It does not say whether a promotion is reversible, what permissions or preconditions are required beyond the evidence gate, or what happens to a lesson that fails the gate.

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?

Three short sentences with no padding and the promotion criteria front-loaded, which is good. The telegraphic style ('Hold/retire retain history') is elliptical enough that meaning has to be inferred, and the section on non-promote actions is compressed to near-zero value.

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?

For a mutation tool with no annotations, no output schema, and 8 mostly undocumented parameters, the description supplies important domain policy that structured fields cannot. It is still incomplete on parameter mapping, return behavior, and the distinction between hold and retire.

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 13% of 8 parameters (only requestId is annotated), so the description must compensate and largely does not. It gestures at acknowledgedCorrections ('review of all current user corrections') and supersedes ('Supersession is atomic'), but project, lessonId, action, reason, and agent are never explained and the criteria are not mapped to any parameter.

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 the three lifecycle transitions (promote, hold, retire) and says history is retained, so an agent can infer this tool changes a lesson's review status. But it never states plainly what the tool does to a lesson — no subject or verb like 'review a lesson and set its status' — and it doesn't distinguish itself from n2_mimir_lesson_propose or n2_mimir_lesson_evidence.

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 promotion gate is spelled out in detail (two distinct completed-work positive applied results, >=80% positive, no negative result, unchanged sources, all user corrections reviewed), which is genuine when-to-use criteria. However, there is no guidance on when to choose hold versus retire, and no mention of the sibling tools that create or supply evidence for lessons.

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