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

The description discloses 'write 3 back,' revealing that this tool writes memories back, which aligns with readOnlyHint=false and adds context beyond the bare annotation. It also notes the model swap and cost, giving the agent useful behavioral expectations without contradicting the annotations.

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?

Each sentence earns its place: behavior, when to use, when not to use, and input contract reference. The parenthetical cost and metadata tags are slightly extraneous but do not bloat the description.

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?

The description covers behavior, cost, selection criteria, and directs to the input schema. With no output schema, a brief note on the return value would be useful, but the overall definition is complete enough for an agent to invoke and reason about the 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 coverage is 100%, and the think parameter's description already explains aliases, truncation, and precedence. The tool description adds no extra parameter-level semantics beyond pointing to the input_schema, so the baseline of 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 behavior: recall 12 memories, reason, and write 3 back, on claude-sonnet-5 instead of haiku. It clearly differentiates this tool from agent-brain by model tier and use case, so an agent can identify what the tool does without opening the schema.

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?

Explicitly names the alternative agent-brain and gives concrete selection criteria: use this tier for multi-step decisions, ambiguous evidence, or senior-escalation-level tasks; use agent-brain for lookups and routine calls. This leaves no ambiguity about when to choose this tool.

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