cabinet_refresh

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

No annotations are provided, so the description carries the full burden, and it does disclose the significant side effects: two files are written/updated, state is committed, and a restart is prepared. What is missing is whether the write overwrites prior last_session.md, whether repeated calls are safe, or what happens on failure.

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, front-loaded with the trigger condition and the main effects, with the optional workflow-recording path placed last. There is little waste, though the '(RP)' abbreviation adds a term the agent must infer without payoff.

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 9-parameter, zero-coverage, unannotated tool, the description explains the overall gesture but not how to populate the inputs. The output schema covers return values, but an agent still cannot tell what belongs in summary or next_move, which are required, making the definition under-specified for the tool's complexity.

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% across 9 parameters, so the description must compensate and largely does not. It loosely covers the optional proposed_workflow_* / stale_workflow_ids group as 'new or retired workflow heuristics,' but never mentions the two required parameters (summary, next_move) or entity_id and files_touched, and it gives no format or content expectations for any of them.

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 concrete operation (executing the Refresh Protocol) and enumerates the artifacts it produces: last_session.md, status_block.md, a state commit, and KV-cache readiness. That is far more specific than a restated name. It does not explicitly distinguish itself from the likely counterpart sibling cabinet_wake, so it stops short of a 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?

A clear trigger is given: use this when context hits roughly 70%, which tells an agent exactly when this tool becomes relevant. It also signals the optional workflow-heuristic path. It does not state when NOT to use it or name cabinet_wake / cabinet_record_workflow as the alternative for related operations.

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