split_pdb

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

With no annotations provided, the description carries the full burden. It discloses an important behavioral quirk: ligands may be classified as ions and 'silently dropped', and HETATM record names may cause missing ligands. It also directs the user to verify output against query_pdb_structure results. While it doesn't cover all possible side effects (e.g., whether input is modified), it reveals a non-obvious failure mode, which is valuable.

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 uses clear section headers (WHEN TO USE, WORKFLOW POSITION, OUTPUT, DECISION GUIDANCE) to organize information. The initial sentence is the purpose statement, and every subsequent section provides actionable guidance without redundancy. It is longer than average but appropriately so given the tool's complexity and workflow integration.

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 when to use, workflow position, output verification, and parameter naming guidance. An output schema exists, so return values don't need to be described. The only minor gap is absence of explicit limitation notes (e.g., unsupported PDB versions), but the provided context is thorough for the tool's purpose.

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%, so baseline is 3. The description adds extra value for output_prefix with a concrete naming example ('my_protein' yields 'my_protein_protein_A.pdb'), which goes beyond the schema's generic prefix description. However, it does not add semantic depth for input_pdb or notes beyond what the schema already states.

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 opens with 'Split a multi-component PDB into separate files by molecular type' — a specific verb+resource+scope statement. This clearly distinguishes the tool from siblings like fix_pdb_structure and assemble_pdb_structures, which serve different stages of the workflow.

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 'WHEN TO USE' section explicitly states the trigger condition (query_pdb_structure reveals a mix of protein/nucleic acid/ligand chains) and gives three concrete example scenarios. The 'WORKFLOW POSITION' section further clarifies placement among sibling tools, providing strong guidance on when to use this tool versus alternatives.

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