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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered structurally. The description adds genuinely useful behavior context — that the default list view returns active and monitoring memories and that these 'gate training', plus default limits (50 for list, 10 for suppressions) — but says nothing about permissions, ordering, or pagination. Solid but not rich.

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?

One dense paragraph with the core purpose front-loaded and per-view details grouped behind middot separators; nearly every clause carries information. The packing is heavy for a single sentence chain, which slightly hurts skimmability, but there is little waste.

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 5-parameter read tool with no output schema, the description usefully describes what each view surfaces (category, status, status history, severity, body_area, held-back progressions), covering the return shape that the schema omits. Remaining gaps — default sort order and whether list is paginated — are minor for a read-only tool.

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 description coverage is only 40%, so the description has to compensate, and it does: it maps category and status to the list view, ties memory_id to detail, and documents limit ceilings per view (200 for list, 50 for suppressions). It doesn't explain, e.g., what status values mean semantically, so it stops short of full compensation.

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+resource ('read' what the user asked Povver to remember) and enumerates the three views with their scopes, so an agent can tell exactly what each mode returns. It also explicitly distinguishes itself from the mutation sibling ('Change them with manage_memory'), making it easy to route between read_memory and manage_memory.

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?

Each view's purpose is spelled out (list = default active/monitoring memories that gate training; detail = per-memory history/severity; suppressions = progressions held back by an injury memory), which effectively tells the agent when to pick each. The read-vs-change boundary is stated via manage_memory, but there is no explicit when-not guidance beyond that.

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