unknowns

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

With no annotations provided, the description carries the full responsibility for behavioral disclosure. It does add meaningful non-obvious behavior: unknowns are not silent negatives, and the tool distinguishes between proven-unresolved and not-crossed. It does not, however, clarify output shape, empty-result behavior, or whether the tool is deliberately query-like with no side effects.

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 compact: two sentences, with the core concept front-loaded and no filler or redundant restatement of the tool name. The phrasing is dense and jargon-heavy, which slightly reduces clarity, but every sentence pulls its weight.

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?

For a tool with 4 parameters, no annotations, no output schema, and a niche conceptual domain, the definition is too thin. It does not state what a result entry looks like, how limit/offset interact with the three described categories, or what 'format=json' adds structurally beyond the schema enum. An agent can understand the intent but cannot accurately predict the call's full contract.

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?

The schema documents only 50% of parameters, and the description adds no parameter-level explanation. limit and offset have defaults but no descriptions, while function is described only as an optional name-or-id filter; the description does not explain how these parameters apply to the 'unknowns' model or whether the result is filtered or aggregated by function.

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 names concrete output categories — unresolved calls, dynamic runtime behavior, and parser/compiler diagnostics — and distinguishes them from ordinary graph lookup by emphasizing the proven-absent versus couldn't-cross distinction. It is somewhat abstract and lacks a clear verb such as 'returns', but an agent can still infer what this tool is for.

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 phrase 'instead of silently treating missing graph facts as none' gives useful guidance about when this tool is relevant, especially when distinguishing true absence from analysis limits. However, it does not explicitly name sibling alternatives or state when not to use this tool, so the usage guidance is clear but only implied.

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