管家记忆-搜索

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states it searches memory, but it does not disclose whether the operation is read-only, how results are ranked, whether empty defaults return everything, or any response shape. For a search tool the agent may need to know it can call it safely without 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 a single short sentence, which is concise, but it front-loads only the basic search fields. It earns a 3 because it is brief and structured as a search statement, but there is room to add a sentence about intended usage or result behavior without bloat.

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 there are no annotations, no output schema, and 4 parameters all undocumented in the schema, the description is too thin. The agent cannot tell what scope/kind values are valid, how results are ordered, or whether this tool is read-only, and it is not differentiated from other memory tools such as memory_context or memory_search.

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 description coverage is 0%, and the parameters have only names, types, and defaults. The description mentions 'full text, scope, kind' which maps roughly to query, scope, and kind, but it does not explain the supported values of scope or kind, what the limit parameter does, or what happens with empty strings. Since defaults are empty for 3 of 4 params, the agent cannot know what an empty query means.

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 says 'search local housekeeper memory by full text, scope, kind'. This is a clear verb+resource combination, so an agent can tell it is a search operation over memory. However, it doesn't distinguish it from sibling tools like memory_update, memory_context, memory_save, or memory_archive, nor from generic 'search'.

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 implies search usage but provides no guidance on when to choose this tool over siblings like memory_context, memory_save, or search. There is no mention of what 'local housekeeper memory' means, what a typical query looks like, or what alternatives exist.

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