Context-first

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'auto-selects based on params' which describes decision logic, and gives brief behavioral hints for each sub-tool (e.g., 'compress with integrity', 'knowledge graph with PageRank'). However, it doesn't disclose important behavioral traits like whether operations are read-only or destructive, performance characteristics, error handling, or authentication requirements.

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 poorly structured and contains unnecessary elements. It starts with '[MEMORY]' which adds no value, includes implementation details like 'use underscores' that don't help the agent, and has a confusing mix of tool documentation and usage instructions. The information about parameter mappings could be presented more clearly. Multiple sentences don't earn their place.

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 complexity (6 sub-tools with different behaviors), no annotations, and no output schema, the description is incomplete. While it covers the basic action-parameter mappings, it doesn't explain what the tool returns, error conditions, or the semantics of operations like 'compact' or 'curate'. For a complex multi-function tool with no structured metadata, more comprehensive documentation would be expected.

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 description coverage is 100%, so the baseline is 3. The description adds significant value by explaining the semantic mapping between 'action' values and required 'params' structures. For example, it specifies that 'store' requires {role, content}, 'recall' requires {query}, etc. This goes beyond what the schema provides by clarifying how parameters interact with actions.

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 lists the 6 sub-tools (store, recall, compact, graph, inspect, curate) which gives a vague sense of purpose, but it doesn't clearly state what the overall 'memory' tool does. It mentions 'hierarchical ingest', 'adaptive gate retrieval', etc., but these are technical terms that don't clearly explain the tool's function. The description focuses on implementation details rather than stating the core purpose.

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 clear guidance on when to use specific actions: 'Auto-selects based on params or use 'action' to override.' It explains the default behavior (auto-selection) and how to override it. However, it doesn't provide guidance on when to use this tool versus its siblings (context_health, context_loop, etc.), which would be needed for a perfect score.

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