memory_consolidation

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

No annotations are present, so the description carries the full burden. 'apply' and 'undo' reveal a mutation/rollback pair, and 'preview' suggests a dry-run, providing some transparency. However, it does not say what applying does to facts, whether undo is always available, or what side effects occur, which is concerning for a tool that can alter memory data.

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 a single efficient sentence, with the resource front-loaded and the action list immediately useful for the required `action` parameter. There is no fluff, and the structure is easy to parse. However, for a 10-parameter, title-less tool, the terseness borders on under-specification.

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?

An output schema exists, so documenting return values is less critical, but the description still omits usage guidance, parameter semantics for most optional parameters, and side-effect behavior. The tool sits among many memory-related siblings, and the description does not provide enough for an agent to choose correct arguments confidently. The action list prevents it from being a 1.

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%, and the only parameter meaning added is that `action` likely maps to preview/apply/undo/list. No guidance is provided for `fact_id`, `proposal_id`, `min_similarity`, `embedding_model`, `consolidation_model`, `status`, `limit`, or `project_key`. With ten parameters, most of the invocation surface is undocumented.

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 identifies the resource ('Fact consolidation') and lists the supported operations ('preview, apply, undo, or list'), making the tool's role clear. It is distinguishable from siblings like memory_recall because it is explicitly about consolidation rather than recall. It stops short of explaining what 'consolidation' actually does, so not 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?

There is no explicit guidance on when to use this tool versus alternatives like memory_recall, pull_truth, or queue_durable_fact. The action list implies preview/list for inspection and apply/undo for mutation, but the description never states conditions, prerequisites, or exclusions. Usage must be inferred.

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