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

Annotations already declare a safe read (readOnly, idempotent, non-destructive, closed-world), so the description adds higher-order behavior instead: that the assistant already consumes memories internally, that calling it unnecessarily is discouraged, and that an empty list should not be surfaced unprompted. That is context the annotations cannot carry.

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 purpose, then routing rules. Dense and mostly waste-free, though the final sentence about empty results could arguably fold into the preceding guidance without loss.

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?

Only one optional parameter, no output schema, and annotations cover safety. The description still covers scoping, when not to call, dedup use, and empty-result handling – everything needed to invoke it correctly.

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% and already documents workspace_id as a UUID from list_workspaces. The description adds the decision rule – omit for personal memories, pass it to scope to a workspace – which tells the agent *when* to set it, not just what it is.

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?

Names the exact resource ('saved memories') and defines what a memory is ('short facts ISMS Copilot keeps as background'). Explicitly contrasts with get_company_context (company facts) and create_memory (dedup check), so an agent can place it among siblings without opening schemas.

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?

Gives explicit triggers ('user asks what ISMS Copilot remembers', 'before create_memory to avoid a duplicate'), explicit exclusions (company facts → get_company_context; don't call preemptively since the system already uses memories), and even guidance on silence for empty results.

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