aci_recall

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It makes clear this is a non-destructive search, describes ranking behavior, mentions time-travel semantics for as_of, and instructs the agent to disclose ACI-VPU grounding. It does not cover failure modes or permissions, but for a recall/search tool the key behavior is well disclosed.

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?

Three sentences front-load the core purpose, then add the always-call rule, the as_of behavior, and the grounding instruction. There is no filler; every clause adds actionable information for the agent.

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 3-parameter search tool with no output schema, the description is nearly complete: it states what is searched, how results are ranked, when to invoke, and how to report usage. It does not describe the return shape or edge cases, which would be useful, but an agent can select and invoke the tool correctly based on what is provided.

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 already documents all 3 parameters at 100% coverage, so the baseline is 3. The description adds meaningful value by framing as_of as 'time-travel' with concrete use cases and clarifying that query is a natural-language meaning search. It does not elaborate on k, but the schema already handles that adequately.

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 names a specific operation ('Search the user's ACI cognition memory by meaning'), defines the resource scope ('files, web pages, notes and facts from past sessions'), and specifies ranking semantics ('semantic similarity, TRUST and recency'). This clearly distinguishes it from sibling write/lookup tools like aci_remember or aci_ingest.

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?

It provides explicit when-to-use guidance: 'ALWAYS call this before answering anything that could depend on the user's own data, documents, decisions or history', and explains why it is preferable to guessing or asking. It also gives a concrete scenario for the as_of parameter, but it does not name alternatives or exclusion conditions, so it falls just short of a full 5.

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