memory_stats

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

Without annotations, the description carries the full burden. It discloses return fields (memory count, type distribution, top 20 tags, importance distribution, keyword frequency) and supports wildcards in queries. It does not state performance implications or error handling, but the detailed return structure provides good transparency for a statistical tool.

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 a compact introductory sentence followed by labeled usage examples and a clear return list. The examples are repetitive in structure but vary in filter combinations, which is helpful for an agent. Minor redundancy exists (e.g., 'memory_stats' repeated many times), but overall it's efficient for the information density.

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 no output schema, the description compensates fully by listing all return fields (count, type distribution, top 20 tags, importance distribution, keyword frequency). The four examples cover all parameter types (no params, query-only, timeRange, combined params, tags). This is complete for a stats tool with optional filtering.

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 75% (3 of 4 parameters have descriptions). The description adds value by showing concrete usage patterns for combining parameters (e.g., query + minImportance, tags only), which the schema alone does not convey. The 'query' parameter's wildcard support is mentioned in both schema and description, but the examples clarify behavior.

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 retrieves memory statistics with optional filtering. It distinguishes itself from siblings like 'remember' and 'recall' by focusing on aggregation stats rather than individual memories, and from 'search' by providing structured distributions rather than raw results.

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 includes five usage examples showing when to use different filter combinations (e.g., query, timeRange, tags), implicitly guiding the agent on when to apply each parameter. While no explicit 'when not to use' is given, the examples clearly demonstrate the tool's scope for aggregated statistics, differentiating it from retrieval-oriented siblings.

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