search_memory

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

With no annotations provided, the description carries the full burden. It communicates that the search is 'raw', implying no ranking, and explains the empty-query behavior. It does not explicitly state read-only status or side effects, but the 'search' action implies a non-destructive operation. This is adequate but not exhaustive.

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?

Two sentences, front-loaded with the core purpose, then the filter list, then the alternative. Every sentence earns its place with zero fluff. The structure is ideal for quick parsing.

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?

An output schema is present, so return-value details are not needed. The description covers all essential usage points: the operation type, filter dimensions, empty-query semantics, and the routing to recall for ranking. For a search tool with seven parameters, this is complete.

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%, so the description must compensate. It lists all filter parameters and adds critical meaning: 'kind' values are enumerated, 'file' is defined as a 'path substring', and the empty-query behavior is explained. It does not mention the 'limit' parameter or tag array format, but overall it provides substantial semantic value beyond the bare 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 clearly states the tool performs a 'raw faceted search across crew memory', specifying a concrete verb and resource. It explicitly names the filter dimensions (kind, tags, author, file, project) and distinguishes itself from the sibling 'recall' by noting that recall provides 'smart ranking instead'.

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 provides explicit guidance on when to use this tool versus the alternative by stating 'Use recall() for smart ranking instead'. It also defines behavior for an empty query ('Empty query with filters lists matches'), giving clear context for invocation.

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