kura_recall

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

Annotations are none, so description carries the full burden. It discloses that an empty result means not remembered, and instructs not to invent. It also explains the meaning-based retrieval and link-following behavior, which is beyond what schema provides. However, it doesn't mention side effects or permissions, but given the tool is a recall (likely read-only), this is sufficient.

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 and front-loaded with the core purpose and usage guidance. Each sentence earns its place: it explains the mechanism, when to use, how to handle empty results, and how to use parameters. No redundancy.

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?

The tool has no output schema, but the description clarifies behavior on empty results. The parameter semantics are fully covered. The complexity is moderate, and the description gives enough context for an agent to call it correctly, including error handling and store switching. It is complete for the tool's 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 coverage is 100%, so baseline is 3. The description adds value by explaining the semantics of 'question' ('as a natural question') and 'store' ('Which kura to ask'). It also explains 'hops' as '[[link]] hops to walk' with a default, which is beyond the schema's basic description. This is a clear added value.

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 recalls from long-term memory by meaning, not keyword, and follows links. It explicitly mentions the resource (kura) and the action (recall), and distinguishes it from keyword-based search. It is differentiated from siblings like kura_read and kura_map by mentioning meaning-based retrieval and link-following.

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 when-to-use guidance: 'whenever the question touches past decisions, measurements, people, machines, or anything done before — prefer it over guessing.' It also tells the agent to say so plainly if empty, avoiding invention. It hints at alternatives (kura_use) for switching stores, and mentions passing 'store' to reach a different kura, which is clear usage context.

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