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

No annotations are provided, so the description carries the full burden. It discloses method-specific behavior (Tversky is asymmetric and alpha/beta tuned), which is useful, but says nothing about auth requirements (an api_key param exists), rate limits, cost, or failure modes.

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?

Front-loaded purpose followed by a compact method breakdown. No filler, though the method block is telegraphic and could note defaults or when each applies.

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?

An output schema exists, so return values need not be explained. Still, for a 6-param tool with no annotations, the description omits api_key handling, SMILES format expectations, and defaults for alpha/beta/method.

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 description coverage is 0% across 6 parameters, so the description must compensate. It adds real meaning for method, alpha, and beta (asymmetric bias control), but leaves smiles_a, smiles_b, and api_key entirely unaddressed.

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 states a specific verb and resource: 'Compare two molecules by structural similarity.' This is clearly distinguishable from siblings like covabasic_substructure or covabasic_fingerprint, though it never explicitly names an alternative to route against.

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?

It explains what each method value does, which implicitly guides method selection (Tversky for asymmetric substructure/superstructure bias). However, it gives no explicit guidance on when to use this tool versus related siblings, nor any prerequisites.

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