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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered. The description usefully adds that results are complete and in canonical node order (deterministic ordering matters for diffing), but says nothing about whether it reflects the last published version, how pagination interacts with that completeness claim, or any auth/scope constraints.

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?

One sentence, front-loaded with the action and resource, then the distinguishing property, then the use cases. No filler and nothing structural to fix.

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 carries the burden of describing return content, and it only does so loosely ('the published graph... in canonical node order'). Given a 4-parameter paginated read against a dense graph tool surface, a note on pagination semantics or the distinction between published vs. working graph would round this 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 100% and each parameter is documented in-schema (cursor, pageSize, projectId, sessionId), so the description need not explain them. It adds no parameter-level meaning of its own, which is the expected baseline here.

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 a specific verb and resource (read the published graph back), and adds a distinguishing trait (complete, canonical node order) that separates it from nearby readers like graph_read, get_context_graph, and get_graph_scope. It stops short of naming any sibling explicitly, so an agent still has to infer which reader it wants.

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 lists intended purposes (diffing, resuming, verifying a mapping), which implies the usage context, but never says when NOT to use it or which sibling reader is the alternative for other needs. That leaves a crowded field of graph readers (graph_read, get_context_graph, get_graph_wiki) without routing guidance.

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