reference

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

Annotations already declare readOnlyHint=true, so safety is covered. The description contributes additional content context by naming the artifact (REFERENCE.md) and its payload (signatures, return shapes, stable error codes), which tells the agent what it will get back. It stops short of describing format or size, keeping it just under full credit.

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?

Two sentences, zero waste, and the highest-value information (use this while writing SDK code) is front-loaded. The sibling-routing clause is compact and earns its place by preventing wrong tool selection.

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?

For a zero-parameter, no-output-schema document retrieval tool, the definition covers purpose, contents, and sibling routing completely. There is no return-value contract to explain and no arguments to document, so nothing an agent needs is missing.

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?

Zero parameters, so the schema imposes no semantic burden and the baseline is 4. Nothing about arguments needs explaining, and the description correctly spends no words on parameter syntax.

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?

States a specific resource (the @gemmein/sdk API reference / REFERENCE.md) and enumerates exactly what it delivers: methods, exact signatures, return shapes, and the error-code table. It also explicitly contrasts itself with `guide` and `search_docs`, so an agent can disambiguate without opening other schemas.

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?

Gives a clear trigger ('while WRITING code against @gemmein/sdk') plus explicit alternatives with selecting conditions: `guide` for conceptual/how-it-works questions and app fit, `search_docs` for pulling a single fact. This is textbook when/when-not/alternative guidance.

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