analyze_graph

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

Annotations already indicate readOnlyHint=true and idempotentHint=true, covering safety and repeatability. The description adds behavioral context: it's premium (implying cost), requires an API key, and computes multiple analytics in one call. No contradictions. A high score as the description adds value beyond 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 four sentences long, front-loaded with the core purpose and key differentiator. Every sentence adds value: purpose, use cases, alternative, prerequisite. No redundant or vague language. Highly efficient.

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 complexity (multiple analytics, premium, sibling tools), the description covers purpose, usage, alternative, and prerequisite. Output schema exists so return values are covered. It doesn't discuss limitations or error handling, but the core information is present. A minor gap in mentioning required parameters explicitly is offset by schema.

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 50% (only sourceGoal and targetGoal have descriptions). The description does not elaborate on nodes or edges beyond mentioning 'directed graph'. It adds no meaning to the node properties (id, type, label, confidence) or edge properties (source, target, type, weight). The description fails to compensate for the low coverage.

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 states the tool computes multiple structural properties (PageRank, Louvain, critical path, bottlenecks) and distinguishes it from the sibling tool plan_pathfind by noting the latter is for simple pathfinding only. The verb 'Compute' and specific metrics make the purpose very clear.

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 explicitly says when to use the tool (for influential nodes, communities, chokepoints) and when not to (for pathfinding alone, use plan_pathfind, which is faster and free). It also mentions the prerequisite ORACLAW_API_KEY. This provides strong usage guidance.

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