recall

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

With no annotations, the description carries full burden. It discloses that the tool returns only key clusters (not memory content) unless inject is true. It explains the trade-offs of inject mode (fewer round trips but lower precision) and details the inject parameters' effects (inject_top_k, inject_prefer_depth, inject_explore_shallow).

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 lengthy but densely informative. It is front-loaded with the critical instruction 'CALL THIS FIRST'. It then covers behavior, follow-up steps, and inject mode in a logical order. Every sentence adds value, though it could be slightly tightened without losing information.

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 no output schema and no annotations, the description is remarkably complete. It instructs the agent on when to call, what to expect, how to proceed after, and provides exhaustive detail on the inject mode. It covers result fields, usage advice, and parameter effects.

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 0%, so description must compensate. It explains query (short focused noun queries) and inject parameters in detail. However, top_k and namespace are not explicitly described; their purpose is only implied by context. Nonetheless, the description adds substantial meaning beyond the schema for the majority of parameters.

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 searches the Key Space and returns canonical key clusters, not memory content. It lists result fields (aliases, key type, etc.) and distinguishes from siblings by explicitly saying what it does not do. The verb 'Search' and resource 'Key Space' are specific.

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 'CALL THIS FIRST before every first response' and provides a clear sequence: select a key, call read_key, then read_memory. It advises short noun queries and decomposition of multi-fact questions. It also explains when to use the inject parameter as an alternative to the normal flow, including trade-offs.

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