List what Luca remembers

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

Annotations already cover read-only, idempotent, and non-destructive status, yet the description goes further by disclosing tier-dependent redaction: fact, reasoning, and quoted evidence are blanked for a redacted-tier key while trust level, lead, and dates always return. It also states the OAuth scope and that workspace can be overridden, which are behavioral facts not in the annotations.

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 core capability and filter list are front-loaded in the first sentence, and the redaction rule is stated compactly. The trailing operational boilerplate ('Does not require idempotency', scope/data-sensitivity lines) is somewhat rote and partially redundant with the idempotentHint annotation, but it is short enough not to obscure the purpose.

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?

With an output schema present, the description need not explain return shapes, and it instead adds the important tier-dependent field redaction rule plus auth scope and workspace override. The remaining gap is filter completeness (state/archived semantics and result limits), which is minor against the schema and output schema coverage.

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 description names several filter concepts (lead -> leadId, scope, source, trust level, free text -> q) that map onto the nested query properties, which the schema itself leaves largely undocumented. It omits the state/archived filters, their defaults, and pagination, so coverage of the filter surface is partial.

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 gives a specific verb ('List') and resource ('what Luca remembers') and enumerates the filter dimensions, so an agent knows exactly what it retrieves. It does not, however, name or distinguish itself from its closest siblings (luca_memory_update, luca_memory_set_archived), leaving that separation to inference.

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 implies when the tool applies by listing available filters (lead, scope, source, trust level, free text) and adds prerequisites like required scopes and workspace override. There is no explicit when-not-this-tool guidance or routing to the memory write/archive siblings, so usage is only implied rather than stated.

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