get_graph

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 clear. The description adds the behavioral trait of being 'bounded,' which is also supported by the maxNodes/maxEdges parameters, but it does not elaborate on default behavior or return format. Given the annotations, the description adds marginal but non-contradictory context; a score of 3 reflects this minimal incremental value.

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 a single, tightly worded sentence with no filler. It front-loads the core purpose ('Return a bounded set of OKF graph nodes and edges') and appends the filtering capability succinctly. Every word earns its place, and the structure is ideal for quick agent comprehension.

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 (9 optional parameters) and the presence of many graph-related siblings (get_subgraph, graph_summary, find_paths), the description is minimal. It does not explain what an OKF graph is, how this tool differs from siblings, or what the output looks like (no output schema). While annotations cover safety, the description lacks guidance on when to invoke this tool, leaving agents to infer from parameter schemas alone. This is adequate but not complete for a tool of this scope.

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 of the 9 parameters has a detailed description. The tool-level description adds no parameter-specific information beyond the generic 'optional concept filters,' which is already implied by the parameter descriptions. With high schema coverage, the baseline of 3 is appropriate; the description does not need to compensate and does not.

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 states a clear action ('Return') and resource ('OKF graph nodes and edges') with a scoping qualifier ('bounded set') and optional filters. It is specific enough to convey what the tool produces, but it does not explicitly differentiate from sibling tools like get_subgraph or graph_summary, which also deal with graph subsets. The phrase 'bounded set' and 'concept filters' hints at distinguishing use cases, but the differentiation is implicit.

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 no guidance on when to use this tool versus its siblings. It does not mention alternatives, exclusions, or prerequisites. The only contextual hint is 'optional concept filters,' which suggests it is for filtered graph retrieval, but it does not compare against get_subgraph, find_paths, or graph_summary. An agent would have no basis to choose this over related tools without deeper inference.

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