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

Goes well beyond the destructiveHint=true annotation by naming exactly what is destroyed and how: duplicate merges redirect edges and tombstone the loser, outcomes are promoted, contradictions become tasks. It discloses safety behavior the annotations cannot: threshold gates reject sweeps that touch too much, and every applied dream keeps preimages and can be reverted.

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?

Front-loaded with the core purpose and staged behavior, then the action map, with no filler. The action sentence is long and packed but each clause carries distinct operational meaning; a slightly tighter structure would earn a 5.

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 complex, destructive, open-world mutation tool with no output schema, the description covers the pipeline, thresholds, LLM dependency, rejection behavior, and reversibility. An agent has enough context to call all five actions safely without needing return-value documentation.

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 100%, so all five parameters and the action enum are already fully documented in the schema. The description restates the action semantics (status/run/diary/revert/configure) but adds no syntax, defaults, or constraints beyond what the schema provides, so the baseline 3 applies.

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?

States a specific verb and resource: a scheduled consolidation sweep over the vault, broken into light, REM, and deep stages. It is unmistakably distinct from every sibling (no other tool performs consolidation or dreaming), so an agent can identify it without opening the schema.

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 description routes each action clearly: status for schedule/state, run to dream now, diary to read entries, revert with id to undo, configure to enable/cadence. It also notes that without an LLM only light runs, which is a real usage constraint. It does not explicitly say when to prefer this over manual curation via siblings, but the tool is unique enough that this is a minor gap.

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