recall

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

The description adds meaningful behavioral details beyond the annotations: it explains the fused search mechanism ('by meaning and keyword'), the project-plus-global scope, and the browse behavior when kind is set without a query. These are not visible in the annotations and help the agent predict the tool's behavior. It doesn't describe return format, but annotations already cover safety.

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 concise, information-dense sentences. It front-loads the core action, states the tool's unique position, and covers the key alternate mode without any wasted words. Every sentence contributes essential context.

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 search tool with 5 optional params and no output schema, the description covers the main modes (search and browse) and scope behavior. It omits the edge case of having neither query nor kind, which might be an error or default behavior, but overall the description is sufficiently complete for an agent to invoke the tool correctly in typical scenarios.

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 the baseline is 3. The description adds value by clarifying the interplay between query and kind (the browse mode) and the 'current project plus global items' scope, which enriches the meaning of the project parameter. This goes beyond the schema's field-level descriptions.

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 explicitly identifies the tool as the search entry point for memories and notes, combining meaning and keyword matching. It also differentiates by scoping to the current project plus global items and mentions a distinct browse mode, making it clear what this tool does versus others.

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 clearly states 'This is the single search entry point,' indicating when to use this tool for search. It also specifies the browse mode when kind is set without a query, providing a clear usage context. It does not explicitly exclude alternatives, but the 'single entry' phrasing is strong guidance.

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