recommend_forcefield

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does add useful context: the tool uses Semantic Scholar for literature guidance when a molecule is not in the library, and it returns structured guidance in that case. However, it does not disclose whether the tool is read-only, whether it makes network calls that could be slow or rate-limited, or what happens on invalid input. This is acceptable for a recommendation tool but not 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 concise and well-structured, with two sentences plus an example list. It front-loads the core purpose, then adds the edge-case behavior, then provides parameter examples. Every sentence earns its place without redundancy or fluff.

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?

The description covers the tool's core function and the fallback behavior, but it does not describe the return format or structure. Since there is no output schema, the agent is left guessing what the recommendation looks like (e.g., force field name, confidence, parameter set). It is adequate for invoking the tool but not for fully interpreting the response, so it falls short of being complete.

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 only specifies 'molecule' as a string with no description. The description compensates by explicitly stating the accepted forms (common name, formula, or IUPAC) and providing concrete examples like 'CO2', 'methane', 'PH3', 'SO2', 'water'. This gives the agent clear guidance on how to populate the parameter, far exceeding the schema's minimal information.

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's function: given a molecule name, it recommends the most appropriate built-in force field and provides literature guidance. This distinguishes it from sibling tools like list_available_forcefields (which lists all force fields) and get_forcefield_files (which retrieves files). The verb 'recommend' and resource 'built-in force field' are specific and unambiguous.

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 context for when to use the tool: when you have a molecule name and need force field recommendation. It also differentiates behavior for molecules not in the built-in library, offering a fallback pathway. However, it does not explicitly state when not to use this tool or mention alternatives (e.g., use list_available_forcefields to see all options), so there is no explicit exclusion or comparison with siblings.

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