brief

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

Despite lacking annotations, the description transparently explains the tool's behavior: it returns a dense, structural brief not meant for human reading. It details the effect of the 'scope' parameter on the output, acting as a 'context-footprint knob,' which informs the agent of resource implications.

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 well-structured with clear sections and code formatting. It front-loads the crucial instruction. While it contains some redundancy (e.g., repeating scope definitions), every sentence adds value, and the overall length is justified by the complexity.

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 tool's complexity (memory brief) and the presence of an output schema, the description adequately covers purpose, usage, and parameter effects. It provides enough context to differentiate from many sibling tools, though it could briefly mention that the output is structured JSON.

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 has three parameters with defaults but zero descriptions. The description adds meaning for 'query' (inline relevant past notes) and 'scope' (full or query mode), but the 'k' parameter is not explained. Since schema coverage is 0%, the description partially compensates but leaves a gap.

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 is a 'Compact Claude-native memory brief' and explicitly instructs to call it at the start of every conversation. It distinguishes itself from sibling tools by its specific function of providing a structured memory overview.

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 provides explicit guidance: 'CALL AT THE START OF EVERY CONVERSATION.' It further differentiates between first use ('full') and mid-session use ('query'), explaining when each scope is appropriate, which is highly instructive.

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