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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the 'frozen Brain Scanner policy' context, which hints at a constrained/closed capability set, but it does not disclose what happens on invalid operations, whether operations are mutually exclusive, or any rate/scope limits. No contradiction with annotations, but little added behavioral value beyond the annotations.

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 short (one sentence), which is concise, but it spends its words on opaque policy jargon rather than useful information. It is front-loaded in the sense of being brief, but the single sentence does not earn its place because it does not clarify the tool's purpose or usage.

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?

This is a complex tool: six operation variants, nested payload objects, multiple optional fields (cursor, pageSize, sessionId, executionId), and no output schema. The description is far too thin to guide an agent through selecting the right operation and payload shape. The annotations cover safety, but the description leaves the agent to reverse-engineer the entire oneOf schema without any semantic guidance.

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, but it mentions no parameters at all. The schema's oneOf structure is complex — six operation variants with different required payload fields — and the description provides zero guidance on which payload fields go with which operation. An agent must fully parse the schema to understand that analyze_impact needs nodeIds while get_graph_scope needs nodeId, etc.

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 says 'Use the closed graph read capability family from the frozen Brain Scanner policy' — it identifies a family of read operations but never states what the tool actually does (reads graph data, analyzes impact, gets roots, etc.). The name 'graph_read' plus the schema's operation enum carry the real meaning; the description itself is vague and jargon-heavy ('closed graph read capability family', 'frozen Brain Scanner policy'). It does not distinguish this tool from siblings like get_graph_scope, get_roots, or graph_sync.

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?

No guidance on when to use this tool versus alternatives. The description references a 'frozen Brain Scanner policy' without explaining what that policy is or when it applies. The schema's oneOf variants imply different operations, but the description does not help an agent choose among them or between this tool and sibling tools like get_context_graph, project_read, or graph_sync.

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