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

Annotations declare read-only, non-destructive, closed-world behavior. The description adds substantial behavioral detail well beyond them: it identifies the RDKit algorithm, the cut modes, the node/edge contents, the cut-limit exclusion ('named and left out'), and the 0-based indexing convention. No contradiction.

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 with the core operation in the first sentence and otherwise dense with useful behavioral facts. The wording is slightly clunky ('how many times the network made it'), but there is little waste for a technically complex tool.

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 purpose, output node/edge content, exclusion behavior, indexing convention, and cut-mode choices; with a full output schema and rich input schema, nothing essential to correct invocation 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?

Schema description coverage is 100%, and the schema already documents 'molecules' and the 'rules' enum values. The description adds some context for 'rules' ('46 BRICS bond types', 'ring-side cuts') but does not meaningfully extend the other parameters, so the baseline of 3 for high schema coverage applies.

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 names a specific computational resource ('the scaffold network') and the exact operation ('as RDKit's CreateScaffoldNetwork builds it') on a defined input ('list of small molecules'), so its purpose is unambiguous and distinguishable from generic molecule tools.

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 never states when to choose this tool over siblings such as cluster_molecules, map_chemical_space, or decompose_r_groups, nor does it give prerequisites or when-not-to-use guidance. It only implies usage from the resource name, so it falls short of actionable usage guidance.

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