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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the truncation disclosure ('long text is clipped') and the field-level semantics for kev and nvd nodes. The clipping note in particular is a behavioral trait an agent cannot get from structured fields.

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?

Front-loaded with the core purpose and the truncation caveat, then the uid provenance, then field semantics. The node-type field enumeration is dense but each item earns its place given there is no output schema.

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?

With no output schema, the description takes on the burden of describing returns and does so for kev and nvd node types, including the important 'cvss_score of 0 means not scored' edge case. It is not exhaustive about other possible node types, which is the main gap.

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?

With 100% schema coverage and a single required uid parameter, the schema already documents the argument fully, including its origin. The description repeats the same sourcing information and adds no format or syntax detail beyond it.

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?

States clearly that it returns one node's properties, with the node identified by uid, which is a specific resource and implicitly a read verb. It does not explicitly differentiate itself from siblings like graph_neighbors or graph_meta, which also return node-adjacent data.

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?

It tells the agent where uid comes from (graph_lookup or graph_search), which is useful prerequisite context, but gives no guidance on when to prefer graph_node over graph_neighbors or graph_meta, nor any when-not condition.

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