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

Selecting a score of 4 is appropriate because no behavioral hints are set (readOnly=false, openWorld=false, idempotent=false, destructive=false), so the description carries the burden. It discloses persistence across sessions, the bounded per-caller/workspace memory pool, and that no personal API key is required. It does not detail what happens when the memory pool is full or whether duplicates are deduplicated, but the disclosed constraints are highly useful.

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 compact and front-loaded with the core purpose. Every sentence adds value: what to store, the operational constraint, the exclusion rule, and a concrete invocation example. There is no filler or redundancy.

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 simple write-only tool with one required parameter, an existing output schema, and already-complete input schema coverage, this description is sufficient. It tells an agent what to store, what not to store, the workspace/caller constraints, and includes an example that demonstrates correct invocation.

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?

The schema already documents all three parameters with 100% coverage, including the kind enum, content constraints, and project scoping. The description adds prose examples and clarifies appropriate content types, but it does not materially expand on the parameter-level semantics beyond what the schema provides.

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 starts with a specific verb and resource: "Persist a durable memory," then enumerates what kinds of content qualify. It clearly separates this tool from its sibling "recall" by emphasizing the write-and-store nature, even without naming the sibling directly.

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 gives clear when-to-use guidance by listing appropriate memory types (decisions, preferences, bug fixes, discoveries) and explicitly says when not to use the tool: "Do not store secrets or raw logs." It does not explicitly name recall as the retrieval alternative, so it stops short of a full routing instruction.

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