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

Annotations already declare readOnlyHint=true, and the description builds on that by disclosing the null return value, session scoping, and the important automatic injection behavior. It clearly explains what the tool does and when its output may be redundant, going beyond the annotation's minimal safety signal.

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?

Three sentences carry exactly the necessary information: the operation and return behavior, the intended use case, and the critical auto-injection caveat. No filler, no repetition of schema fields.

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 read-only getter with full schema coverage, the description is complete. It addresses the return value, session scope, when to call it, and when not to call it. No output schema is needed for this tool, and all necessary behavioral context is present.

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 100%, so the parameters are already well-documented. The description adds context about the purpose of (kind, key) in relation to existing state and the same key used in setWorkingMemory, but it does not materially extend the schema's per-parameter semantics. Baseline 3 is appropriate.

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 states a specific verb+resource: 'Retrieve the current state for a (kind, key) in the current session.' It clearly distinguishes this get-by-key operation from sibling tools like listMemories, countMemories, and searchMemory, and adds the key behavior of returning null if unset.

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 explicit when-to-use guidance: 'Use this when you need to merge into existing state or verify what's stored.' It also provides a strong when-not-to-use note: active entries are auto-injected into the system prompt by Build Messages, so manual calls are usually unnecessary and should only happen for on-demand full state.

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