brain_stats

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

Discloses behavior beyond basic function: it reads local metadata only and makes no LLM or embedding calls. The returned data is specified, and there is no indication of side effects or hidden costs, making the tool's behavior fully transparent.

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 structured with clear sections (Behavior, Reads, Usage) and is concise yet complete. Every sentence adds value, and there is no redundant or vague content.

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?

Even without an output schema, the description enumerates the exact return fields (path, counts, models, settings) and provides usage context. The tool's purpose, behavior, and expected output are fully understandable from the description alone.

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 input schema is empty and the description explicitly states 'Takes no parameters.' There is no ambiguity about expected inputs, and the schema coverage is complete by virtue of having no parameters.

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 reports what the index currently contains and enumerates specific returned metrics (store path, total chunk count, per-file chunk counts, embedding/chat models, retrieval settings). It is unambiguous and easily distinguished from sibling tools that query or modify the index.

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?

Provides explicit usage scenarios: call before searching, after ingestion, or when answers seem incomplete. Also notes it reads local metadata only, implying a lightweight, safe alternative to tools that invoke LLM/embeddings.

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