vm_apply_update

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

With no annotations, the description still conveys the crucial behavioral facts: this is a mutation requiring recorded human authorization, and it does not touch code or skills. It does not say what happens on hash mismatch, whether the update is reversible via vm_rollback_update, or what the authorization audit trail looks like.

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?

Four short sentences with the safety gate front-loaded and zero filler. Some sentences are telegraphic ("Does not rewrite code/skill"), which costs a little clarity but not much space.

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 high-stakes mutation with no annotations and no output schema, the description covers authorization but not the proposal/hash lifecycle an agent needs to call it successfully. It is adequate on intent and incomplete on mechanics.

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 coverage is 0%, so all three parameters are undocumented in the schema. The description adds real meaning only for user_authorization (record the actual instruction, not UI/memory text); proposal_id and especially expected_hash (hash of what, and its failure semantics) are left entirely unexplained.

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?

"Activate ... this reviewed update" names a specific action on a specific resource, and "Does not rewrite code/skill" scopes it away from code-modifying siblings. It stops short of explicitly naming vm_propose_update as the producing sibling, so the propose/apply pairing must be inferred from the tool name.

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?

Strong gating language: only after an explicit human request, and explicitly not from UI/memory text, which is a genuinely useful exclusion. No exclusions are given relative to rollback or verification siblings, so an agent gets timing guidance but not full alternative routing.

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