memory_graph_review

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains what each action does (e.g., 'dismiss_pair' marks distinct, 'accept_junk' deletes an artifact, 'propose' never writes directly) and notes error behavior. However, it does not address reversibility or side effects beyond the immediate action, leaving some room for improvement.

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 front-loaded with a concise purpose, then organized into terse action bullets. Each sentence earns its place; no fluff. The length is appropriate for a tool with nine distinct actions and multiple parameters.

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 the tool's complexity (7 parameters, 9 actions, no annotations, output schema present), the description is remarkably complete. It covers the queue context, every action with its required parameters, and the return behavior ('per-action dict; {error} on a bad action or missing input'). The existence of an output schema means return details need not be spelled out.

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%, so the description must compensate, and it does excellently. Each action bullet maps parameters to their roles (scope for list, src/dst for dismiss, proposal_id for settle, proposals for propose), and even clarifies format for 'dismiss_slot_pair' ('entity|attribute' keys). This adds substantial meaning beyond the bare 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 identifies the tool's purpose: 'Work the graph review queue — deep-dream proposals that need a verdict before they touch the real graph.' This is a specific verb+resource, and the listed actions (accept, reject, dismiss, etc.) differentiate it from sibling tools like memory_graph_relate that directly mutate the graph.

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 provides clear context for when to use the tool: it handles proposals that must be reviewed before affecting the graph. It implicitly contrasts with direct graph tools via 'never written directly' for propose, but it does not explicitly name alternatives or state exclusions, so it falls just short of a 5.

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