ariadne

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it's read-only with an exception ('no writes except an implicit positive feedback row if called within 10 min of a matching query_chains'), returns up to 3 source nodes × up to 10 neighbours, includes a 'stale_warning' field with a recommendation to call 'rescan', and explains matching logic ('Partial, case-insensitive match against node id and raw_name; ambiguous inputs return multiple source groups'). This covers most critical aspects, though it could mention error handling or rate limits.

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 appropriately sized and front-loaded, starting with the core purpose and key details. Most sentences add value, such as explaining usage guidelines and behavioral traits. However, it could be slightly more streamlined by combining some clauses, and the second paragraph might benefit from clearer separation of ideas.

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 of the tool (with behavioral nuances like implicit writes and matching logic), no annotations, and no output schema, the description does a good job of covering essential context. It explains the tool's purpose, usage, behavior, and parameter semantics comprehensively. However, it lacks details on the output structure (e.g., what fields are in the return value beyond 'stale_warning'), which would be helpful since there's no output 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?

The input schema has 100% description coverage for the single parameter 'name', so the baseline is 3. The description adds meaningful context beyond the schema by explaining the matching behavior ('Partial, case-insensitive substring match against both id and raw_name'), advising to 'Prefer exact names copied from a prior query_chains result to avoid ambiguity', and noting that 'very short strings (e.g. 'get') will match many nodes and only the first 3 are expanded.' This enhances understanding of how the parameter is used.

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 specific action ('One-hop neighbours of a known node') and resources involved ('endpoint / Kafka topic / GraphQL operation / frontend call'), distinguishing it from sibling tools like 'query_chains' by specifying it's for tracing further after having a concrete node name. It avoids tautology by not just repeating the tool name 'expand_node'.

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 explicit guidance on when to use this tool ('Use AFTER query_chains when you already have a concrete node name and want to trace one hop further') and when not to use it ('Use query_chains (not this) when starting from a business term or when you don't yet know a node name'), clearly differentiating it from the sibling tool 'query_chains'.

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