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

Annotations already declare readOnlyHint/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: answers are grounded in recorded data, and the tool explicitly says so when it does not know (abstention behavior). It omits any note about latency/cost of deeper reasoning, but the core behavior is 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?

Two short sentences with illustrative examples and the read-only guarantee front-loaded; no filler. Every clause carries information useful for selection.

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 and annotations covering the safety profile, the description need not explain return values or permissions. It covers purpose, grounding, and abstention adequately for a 7-parameter tool; only explicit sibling routing 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?

Schema coverage is 100%, so the schema already documents all seven parameters, including the non-obvious peer_id/target_peer_id relationship, defaults, and the reasoning_level enum. The description adds nothing beyond this, so the baseline 3 applies.

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 action and resource: ask memory a natural-language question and receive a written, grounded answer. The examples ("Where does the user live?") make the resource and output shape concrete. It does not explicitly distinguish itself from the sibling `search`, though the NL-question framing implicitly separates it.

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?

Usage is implied through the examples and the read-only framing, but there is no explicit when-to-use guidance or routing against alternatives in the sibling set (`search`, `get_peer_card`, `list_conclusions`). An agent can infer intent but is not told when this beats a plain search.

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