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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description genuinely adds behavioral detail beyond annotations: the inference path where facts requires 'memories' in include, the empty-list behavior for hypotheses/rules, and the 15/10 caps. However, it does not describe the return object's structure in depth or error conditions. With annotations carrying the safety profile, a 3 is appropriate – useful additions but not fully rich behavioral coverage.

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?

Front-loaded with the core purpose, then organized as bullets per module, a Returns block, and an Args block. Every line carries needed information for a 6-param, multi-module tool; no repetition of annotation fields.

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 6-parameter tool with an output schema present, the description is complete enough: it explains module semantics, the include-based inference dependency, time-window scoping, and the alternatives. Output structure is summarized even though the output schema already covers it, so nothing an agent needs to call correctly is missing.

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?

With 0% schema description coverage, the description carries the full burden and does document all 6 parameters: topic, entity_id, include (subset of four modules with default all), and time_range/since/until scoped to the memories module only. That is meaningful semantic value beyond the bare param names. Minor gap: since/until format details ('ISO-8601') are thin and include's array item type is undocumented beyond the enumerated values.

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 opening sentence names a specific verb ('Get what NEXUS has stored'), the resource (memories, facts, hypotheses, rules), the return shape (one structured object), and the read-only scope. It also names the sibling tools (retrieve_memories, get_facts_by_entity, list_hypotheses) to route away from them, so an agent can distinguish it without opening the schema.

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 states the condition that selects this tool ('one read-only call' spanning multiple kinds) and the alternatives ('For a single kind of data, use retrieve_memories, get_facts_by_entity or list_hypotheses instead'). It also documents the include/entity_id dependency that changes fact behavior, giving the agent concrete invocation context.

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