vm_review

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

No annotations are supplied, so the description carries the full burden; it does disclose two genuinely useful behavioral traits — the write is atomic, and it 'Never infers success or activates learning' (an explicit negative behavior). It still omits what the recorded experience does downstream, error/idempotency behavior, and what happens to the required capture_id if stale, which matters for a mutation tool with zero annotation coverage.

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?

It is compact and front-loads the action, but the first sentence is a run-on of stacked jargon and the body-field list is crammed into a second clause without formatting. Most of the content earns its place, yet the phrasing makes it slower to parse than a short bulleted structure would.

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 a nested body object, no output schema, and no annotations, the definition does cover the most complex part (the body shape) and one hard precondition. It still leaves the top-level required identifiers, the return value, and the relationship to sibling memory tools unexplained, so it is adequate but not complete.

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% and the body is an untyped open object, so the description adds real value by enumerating body fields (objective, next_step, scope, outcomes[{action_id,success,note,prior_session?}], verified/uncertain/evidence/lesson). But the three required top-level parameters — session, owner_thread_id, capture_id — are never explained beyond the implicit hint in 'Requires a fresh post-action image', leaving half the surface undocumented.

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 verb 'record' and the objects ('checked outcomes, checkpoint and pending factual experience') are present, so the general intent is discernible, but the phrasing is heavy jargon ('atomically record checked outcomes', 'pending factual experience') that leaves the exact effect ambiguous. It also does not distinguish itself from siblings that appear to cover overlapping ground (vm_checkpoint, vm_verify, vm_experience), so an agent cannot tell from this text why it should pick vm_review over those.

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?

'At a meaningful outcome' and 'Requires a fresh post-action image' imply the trigger condition and a precondition, which is real guidance. However, it never names an alternative or an exclusion — nothing says when to use vm_checkpoint or vm_verify instead, or what happens if no fresh image exists.

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