recall

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

No annotations are provided, so the description must carry the burden. It discloses that results include 'auto-attached lessons' and instructs to 'read & FOLLOW them,' which is a significant behavioral directive. It also provides a trust threshold for interpreting results. However, it does not state whether the tool is read-only or what happens with the project parameter, so it is transparent 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?

The description is four concise sentences, front-loaded with the core action. The call format, return list, and trust threshold are all packed into a tight paragraph without waste.

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 core usage, return composition, and the important 'follow lessons' directive. The output schema presumably handles return structure, so that is not a gap. However, the project parameter is never mentioned, and there are no error handling or limit notes, so completeness is moderate.

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% and the description only provides the call format 'recall(query, top_k=5).' It does not explain the meaning of top_k (number of results) or the project parameter, which is entirely omitted. This is a clear gap given the schema has three parameters.

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 specific verb and resource: 'Search memory for anything about the user/past/project.' This clearly distinguishes it from sibling write tools like record_keyed_fact and from the more specific find_lessons. The call format reinforces the purpose.

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 this is the general memory search tool by saying 'anything about the user/past/project.' It includes operational guidance like the trust threshold but does not explicitly state when to prefer it over find_lessons or session_brief, nor any when-not conditions. Thus, usage is implied rather than explicit.

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