dream

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

With no annotations, the description carries full burden and does exceptionally well. It discloses that the tool recomputes findings on each call (implying side effects), explicitly excludes the model/compaction passes, clarifies that persisted findings from prior runs still surface, and mentions the stable `id` for review. This gives the agent a clear picture of behavior and side effects.

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?

The description is well-structured and front-loaded with the core return value, but it's slightly verbose with the 'pull surface' metaphor and a bit of redundancy between 'deterministic' and 'Recomputes the deterministic findings'. Still, every sentence adds meaningful context, so it earns a 4 rather than 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?

The tool has no output schema and no annotations, so the description must explain return value, behavior, and limitations. It covers the worklist composition (coverage gaps + stale references), ranking, stable IDs, the recompute side effect, the exclusion of model passes, and the fact that prior persisted findings surface. It also points to dream_review for follow-up, making it complete for an agent to decide when to invoke.

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 the description is not required to explain parameters. The description adds no parameter-specific semantics beyond the schema, which already covers `all` and `limit` with descriptions. Baseline 3 is appropriate.

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 clearly states the tool returns a deterministic memory-maintenance worklist of coverage gaps and stale references, ranked with stable IDs. It distinguishes itself from the sibling tool dream_review by pointing to it for reviewing findings, and differentiates from the broader read/memory tools.

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 explicitly identifies this as the 'pull surface' for burning down the worklist, explains it recomputes deterministic findings on each call, and clearly states it does NOT run the opt-in model verdict/compaction passes (those stay on CLI/cron). It also directs users to dream_review for reviewing findings, providing clear when-to-use and alternative guidance.

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