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

With no annotations, the description bears full burden. It discloses that inference is CPU-bound and may take up to ~60s, which is useful. However, it does not mention requirements (e.g., model availability), error behavior, or side effects. Some behavioral context is provided, but not comprehensive.

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 two sentences, front-loading the core purpose and key behavior. Every sentence adds value: the first defines purpose, the second provides behavioral context. No unnecessary words.

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 tool with 4 parameters and no output schema, the description explains the output concept (pKd) and mentions the model. However, it does not describe the return format or data structure, which is a gap given the lack of output schema. Additional context like validation rules or typical values would improve completeness.

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 schema already describes all 4 parameters with 100% coverage. The description adds minimal new semantic detail beyond the schema; it mentions the model (IBM MAMMAL) but does not clarify optional parameters (norm_y_mean, norm_y_std). Baseline 3 is appropriate.

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 predicts drug-target binding affinity as pKd, a specific metric. The verb 'Predict' and resource 'drug-target interaction' are explicit. It distinguishes from sibling tools like predict_clintox (clinical toxicity) and predict_ppi (protein-protein interaction).

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 lacks guidance on when to use this tool versus alternatives such as predict_clintox or predict_ppi. No when-to-use or when-not-to-use information is provided, leaving the agent without context for selection.

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