statewave_search_memories

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

No annotations are provided, so the description must disclose all behavioral traits. It correctly states 'Read-only' and explains that it searches only compiled memories (not raw episodes), returns results ordered by relevance, and returns an empty array for no match. The description covers the key behaviors, but could mention whether the search is expensive or if there are any rate limits. Still, it is thorough enough for an agent to understand the tool's side effects and data dependencies.

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 three sentences long, front-loaded with the primary purpose and read-only nature. The second sentence adds a critical constraint, and the third sentence covers return format and usage guidance. Every sentence is essential and there is no redundant or unnecessary text.

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 that there are no annotations and no output schema, the description covers the necessary aspects: purpose, when to use, key constraint (compilation), return format, and an example of empty results. It is complete enough for an agent to use the tool correctly, though it could elaborate on what 'compiled, durable memories' means beyond referencing statewave_compile_subject.

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%, but the description adds significant value beyond the schema. It explains that the search operates on 'distilled memories' and that newly ingested episodes require prior compilation, which clarifies the meaning of the search results. It also provides formatting guidance for the 'subject' parameter. This extra context elevates the score above the baseline of 3.

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 action ('Search'), the resource ('compiled, durable memories'), the method ('free-text query'), and the outcome ('most relevant ones, ranked by relevance'). It explicitly differentiates from sibling tools like statewave_get_context which assembles prompt-ready context. The purpose is unambiguous and 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 when to use this tool ('look up specific remembered facts') and when to prefer an alternative ('prefer statewave_get_context when you instead want prompt-ready context assembled to a token budget'). It also provides a critical constraint: newly ingested episodes only appear after statewave_compile_subject has run, guiding the agent on prerequisite actions.

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