search

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

It adds a useful behavioral detail—case-insensitive matching—beyond what the input schema states. However, no annotations are provided, and the description does not disclose whether the search is read-only, how results are returned, whether partial matches are supported, or if there are result 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?

One short, front-loaded sentence with no fluff: the action, target, and key behavioral trait are all stated immediately. Every word earns its place.

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?

For a simple two-parameter search tool, the description is adequate for basic invocation, especially given full schema coverage. However, with no output schema, no annotations, and closely related sibling tools ('search_context', 'recall'), the description could be more complete by noting result shape, limitations, or a pointer to alternatives.

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 100%, so parameter names and descriptions already document 'query' and 'folder'. The description adds context by specifying that the query searches titles and contents case-insensitively, but it adds no detail about query syntax, wildcards, or folder path format beyond the schema.

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 states a specific verb ('search'), a resource ('memory titles and contents'), and a behavioral qualifier ('Case-insensitive'). It clearly distinguishes from list-like siblings, but it does not explicitly distinguish itself from closely related siblings such as 'search_context' or 'recall'.

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 the tool is for keyword matching over memory titles/contents, but it gives no explicit guidance on when to prefer it over alternatives like 'search_context' or 'recall'. It states what it searches, but not when it should or should not be used relative to siblings.

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