dream

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

With no annotations, the description fully discloses that the tool recomputes findings on each call, syncs dream_findings (classified as a write tool), and does NOT run model passes. It also explains the deterministic nature.

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 informative but not overly verbose. It front-loads the core purpose and then adds necessary details. Slightly dense but earns its length.

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 description is thorough given the tool's complexity. It covers return type, recomputation behavior, what is excluded, and references sibling tool. No output schema exists, but the description compensates well.

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 100% (parameters are well-described in schema). The description adds context: 'all' surfaces human-reviewed findings, 'limit' controls the load-bearing-symbol budget, providing meaning beyond the schema.

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 the deterministic memory-maintenance worklist (coverage gaps and stale references) with stable IDs for review. It distinguishes from siblings by specifying that it does not run opt-in model passes.

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 states it is 'the pull surface for a strong agent to burn down the worklist' and clarifies that model verdict/compaction passes are on CLI/cron, not this tool. It also mentions reviewing findings with dream_review.

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