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

The annotations already declare readOnlyHint=true, so the description adds value by disclosing that 'full' detail requires a reason (10–200 chars) and is audit-logged under MEMORY_EXPORT_GOVERNANCE_V1. It also clarifies that 'summary' returns redacted metadata with no plaintext, providing transparency beyond the annotation. However, it does not describe return metadata structure or failure modes beyond the reason requirement.

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?

The description is concise with two sentences, front-loading the core purpose and then detailing the two modes. It is efficient but could be slightly more structured with clearer separation of default vs. advanced usage.

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?

Given the output schema exists (handling return values), the description adequately covers initialization behavior and the two detail modes. It is complete enough for a read-only tool with clear parameter documentation, though it could mention any side effects or persistence behavior.

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 documents both parameters well. The description adds meaning by explaining that 'summary' is the default and returns redacted metadata only, while 'full' requires reason and is audit-logged. It also states that without reason, 'full' will fail with code -32602, which is valuable context not in 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?

The description clearly states the tool initializes a persistent memory context for a conversation or agent session, specifying the verb 'Initialize', resource 'persistent memory context', and the recipient 'conversation or agent session'. This distinguishes it from siblings like 'list_memories', 'recall', and 'store_memory', which are about listing, recalling, or storing memories rather than initializing a context.

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?

The description explains when to use each detail level: 'summary' for default redacted metadata, 'full' for plaintext content when a reason is provided. It implicitly guides usage by stating requirements for 'full', but does not explicitly contrast with sibling tools or state when not to use this tool.

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