recall

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

Without annotations, the description carries the full burden of behavioral disclosure. It does explain the graph-aware recall behavior for the 'neighbors' parameter, which is valuable and non-obvious. However, it does not explicitly state that this is a read-only operation or mention any side effects, rate limits, or other behavioral nuances, leaving some gaps.

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 concise and front-loaded, with a first sentence stating the core purpose. The Args section is structured with each parameter on its own line and brief, useful explanations. There is no redundant or filler content; every sentence 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?

The description covers the tool's purpose, usage context, and all parameters. An output schema exists, so the lack of a return-value description is acceptable. The tool is simple, and the description provides sufficient context for an agent to select and invoke it, though it lacks explicit alternative tool guidance.

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?

The schema provides no parameter descriptions, so the description fully compensates. Each parameter is clearly explained: query as 'Natural language query', project with scoping semantics (None = search all), limit as 'Maximum number of results', and neighbors with a detailed explanation of graph-aware recall. This goes beyond basic schema information, especially for the complex 'neighbors' behavior.

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 opens with 'Search the Brain semantically,' which clearly identifies the action (search) and the resource (the Brain). It also states 'Use this to find relevant memories before starting work,' providing clear context. However, it does not explicitly distinguish this tool from siblings like 'related_memories' or 'recall_associative', so it lacks explicit differentiation.

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 tells the agent when to use this tool: 'Use this to find relevant memories before starting work.' This provides a specific context. It does not mention alternative tools or exclusions, but the stated use case is clear enough to guide selection.

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