search_unified

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently explains pagination behavior, the need to increment 'page' when results are not found on the first page, and the exact return structure (results + pagination metadata). It also states validation errors (ValueError). While it doesn't explicitly mention read-only or side-effect-free behavior, that is inherent in a search operation and does not detract significantly.

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 well-structured with clear sections for pagination, arguments, return values, examples, and exceptions. It is detailed but every sentence serves a purpose; the examples and parameter constraints are essential given the schema's lack of descriptions. The front-loaded purpose and logical organization make it easy to parse, and no content feels redundant.

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 the tool's complexity (9 parameters, no annotations), the description is exceptionally complete. It covers all parameters, pagination flow, return format, error handling, and provides concrete usage examples. Even though an output schema exists, the description's return summary adds context about pagination metadata. This is a well-rounded, self-sufficient description.

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 input schema has zero description coverage, so the description must fully compensate. The 'Args:' section provides comprehensive, semantics-rich explanations for all 9 parameters, including constraints (max query chars, max tags, numeric ranges, defaults) and the meaning of each weight/filter. This goes far beyond the bare schema and is exactly what an agent needs to invoke the tool correctly.

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 a clear, specific action: 'Search across both STM and LTM with unified ranking.' This verb+resource combination immediately distinguishes it from sibling tools like search_memory, which likely targets a single memory store. The phrasing is neither tautological nor vague, and it sets accurate expectations for a cross-memory 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 clearly implies usage for combined STM/LTM search and provides detailed pagination guidance, including how to navigate large result sets and retrieve subsequent pages. However, it does not explicitly name alternatives or state when NOT to use this tool (e.g., when only one memory store is needed). This clear context without exclusions aligns with a score of 4.

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