cuemap_recall

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

With no annotations, the description carries the full disclosure burden and mostly meets it: it specifies the return envelope (engine JSON with project_id/memory_id handles, source metadata, diagnostics in text and structuredContent) and the hybrid reranking behavior. It stops short of disclosing side effects such as auto_reinforce altering stored memory state, a notable gap for a tool that can mutate memory.

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?

Four sentences with no filler: purpose, output shape, sibling routing, and operational guidance each get roughly one sentence. The final sentence is slightly dense, packing three separate pieces of advice, but nothing is wasted.

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 30-parameter tool with no output schema and no annotations, the description covers the essentials: what it returns, how to follow up with cuemap_memory_get, and how to start with safe parameter values. Gaps are the auto_reinforce side effect and empty/error behavior, but the core call-and-follow-up flow 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 coverage is 100%, so the schema already documents all 30 parameters; the description adds cross-cutting guidance beyond it — small limit, depth 1, and enabling reconstruction only when surrounding evidence is needed — which maps onto limit, depth, and the reconstruction/fusion parameters. It does not explain how mode parameters interact, but the baseline is already satisfied by the 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?

States a specific verb and resource — 'Recall evidence for a focused question' — and distinguishes itself from the sibling cuemap_memory_get by describing the returned handles and how they are used downstream. The scope (focused recall with follow-up narrowing) is concrete enough that an agent can tell this from ingestion and artifact tools.

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?

Explicitly routes to cuemap_memory_get when the stored record is needed, naming the key sibling alternative. Operational starting points — 'Start with a small limit and depth 1; enable reconstruction only when surrounding evidence is needed' — give concrete parameter-level guidance. It does not, however, contrast with the wider sibling set (e.g., when to prefer ingestion or intent classification).

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