memory_dream

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

With no annotations, the description carries the full burden and succeeds. It discloses that status is read-only, deep is dry-run unless apply=true and snapshots graph tables first, pull writes facts and commits cursors, rollback reverts facts and events but preserves traces/cursor, and responses are per-action dicts with {error} on bad input.

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 structured as a short purpose line plus per-action bullets, with each line earning its place. It packs substantial semantics into compact wording without unnecessary repetition.

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?

Given six parameters, seven sub-actions, no annotations, and broad sibling context, the description covers all actions, all side effects, the main workflow patterns, and the error/return convention. Nothing critical an agent needs to call or chain this tool is missing.

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%, but the description documents every parameter in context: limit bounds pulls, cursor is the newest pulled timestamp for commit, apply controls deep's dry-run, snippets controls evidence inclusion, and run_id targets a rollback pass. This fully compensates for the empty schema descriptions.

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 clear resource (memories undergoing consolidation) and gives each sub-action a concrete verb and object: status, pull, run, deep, runs, rollback. It differentiates manual pull-and-commit flow from server-side run and full-corpus deep, so an agent can tell this apart from sibling tools like memory_consolidate or memory_graph_review.

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 gives usage context for every action and names downstream tools to call: memory_fact_set for writing facts, memory_graph_review for settling candidates. It lacks explicit when-not-to-use statements against siblings, but the action workflows effectively tell an agent how to orchestrate the dream process.

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