get_model_recommendations

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

No annotations are present, so the description carries the transparency burden. 'Calculates' indicates a non-mutating computation, which is useful, but the description does not explicitly state the return format, confirm no side effects, or explain how optional inputs like warmth influence results.

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 a single front-loaded sentence with no filler. Every word contributes either the output set or the input basis.

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 simple calculator with no output schema, the description names its outputs but does not describe the return object shape or clarify how the optional warmth parameter factors into the calculation. Sufficient for basic invocation, but not fully 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?

Schema coverage is 100%, providing the baseline of 3. The description adds meaning by mapping 'LLM parameter size' to parameter_size_b and introducing 'query complexity' as the role of user_message, which the schema labels only as 'User's prompt message'. Warmth's role remains unexplained.

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 uses a specific verb ('Calculates') and names a precise resource: adaptive sampling parameters, listing five concrete outputs. This makes the tool clearly distinct from sibling scripture/context tools despite the broad 'model recommendations' name.

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 intended use is implied: when an agent needs sampling parameters derived from model size and query complexity. However, the description never states explicit when-to-use conditions, exclusions, or alternatives (though no sibling tool appears to overlap).

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