Server Quality Checklist

Tool Scores

• reset_workflow_reportA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral burden. It discloses that the tool clears the session report, starts a fresh record, and creates a new timestamped file per reset. It does not discuss whether old files are preserved or return specifics, but the output schema helps fill that gap.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is compact and front-loaded, with a clear one-line purpose followed by a short WHEN TO USE block. Every sentence adds value and there is no filler or repetition.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple tool with one optional parameter and an output schema, the description covers purpose, timing, and reset semantics. It could be slightly more explicit about whether previous report files are preserved, but that word 'new timestamped file' implies non-destructive behavior.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% for the single optional report_file parameter, which is fully described in the schema. The description adds no parameter-specific meaning, but the baseline of 3 applies when the schema already explains the parameter.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with 'Clear the session workflow report and start a fresh record,' which is a specific verb and resource. It clearly distinguishes itself from sibling tool get_workflow_report, which reads the report rather than resetting it.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The 'WHEN TO USE' section explicitly states to call at the start of a new structure-preparation task when a clean report is needed, and explains the rationale (avoiding previous work). It does not name explicit exclusions or alternative tools, but the context is clear enough.

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

• query_pdb_structureA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description fully carries the behavioral burden. It goes beyond a simple read operation by explaining how to interpret output fields (e.g., chain types, numbering gaps, structural breaks) and their practical implications (e.g., ligand chains cannot be relaxed with built-in presets). This is rich useful context, though it doesn't explicitly state that the tool is non-mutating, which is implied by 'Inspect'.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-structured with headings (WHEN TO USE, WORKFLOW POSITION, OUTPUT — WHAT TO CHECK) and bullet points. It is longer than average, but each section earns its place by explaining workflow and output interpretation. The main purpose is front-loaded in the first sentence.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Despite having an output schema, the description adds substantial interpretive value that the schema alone would not provide (e.g., what a structural break coinciding with a numbering gap means). It covers the tool's role in the workflow and gives the agent enough context to act on the results. For a query tool with this complexity, it is complete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%: both input_pdb and notes have clear descriptions. The tool description does not add parameter-specific details beyond the schema, but none are needed since the schema already documents the parameters well. Baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a specific verb and resource: 'Inspect a PDB file and return a detailed chain-level summary.' This clearly distinguishes it from sibling tools like fix_pdb_structure or relax_pdb_structure, which modify rather than inspect. The tool's role is unmistakable.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Explicit guidance is provided: 'Always call this FIRST before any fixing or relaxation' and 'Step 1 of every session.' It also advises re-running after split_pdb for per-component details. This directly tells the agent when to use this tool versus alternatives, and even names alternatives in context.

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

• get_workflow_reportA
  4.5/5.0
  Behavior4/5

  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 that the report is automatically written after every tool call, that this tool does not produce the file, and that save_to optionally copies the report to an additional path. This is strong disclosure of side effects and behavior, though it could also mention error handling or file permission requirements.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is concise and well-structured. The primary purpose is front-loaded in the first sentence, and a clear 'WHEN TO USE' section follows with an organized bulleted list. Every sentence contributes value; there is no fluff or repetition.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's simplicity (one optional parameter, output schema available) and the rich context provided—purpose, usage guidelines, automatic file behavior, and side effects—the description is complete. It adequately covers all necessary aspects without needing to explain return values, as the output schema exists.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% (one optional save_to parameter with a detailed description). The tool description repeats the parameter's purpose ('Optionally copy the report to a different path via save_to') but adds no new meaning beyond the schema. Baseline of 3 applies because the schema already documents the parameter fully.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose with a specific verb and resource: 'Return a summary of all tool calls and LLM decisions made in this session.' This distinguishes it from siblings like reset_workflow_report, which implies resetting rather than retrieving.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The 'WHEN TO USE' section explicitly explains when to call this tool and when not to, noting that the report is auto-generated after every tool call. It lists concrete use cases (telling the user the report location, copying via save_to, reading the markdown string) and clarifies that producing the file is unnecessary.

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

• fix_pdb_structureA
  4.7/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden. It discloses key behaviors: adding hydrogens, adding missing heavy atoms, mapping nonstandard residues, removing heterogens, and modeling missing residues/termini with associated risks. It also explains consequences like clashes from large loop gaps and slow minimization with water. It could be slightly more explicit about whether the input file is modified or a new output file is written, but the output_pdb parameter and output-check section imply this.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is long but exceptionally well-structured with clear headers (WHEN TO USE, WORKFLOW POSITION, DECISION GUIDANCE, OUTPUT). Every sentence has a purpose and front-loads the most critical workflow information. Despite its length, it remains scannable and directly actionable.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a complex tool with 13 parameters, the description is remarkably complete: it gives workflow position, parameter decision rules, and output interpretation guidance. The output-check section even tells the agent what anomalies to flag (e.g., unexpected nonstandard conversions, many missing atoms, zero heterogens removed when ligands were present). This covers both correct invocation and downstream validation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the baseline is 3. The description adds significant value beyond the schema by explaining semantic choices for chains_to_keep/remove, ph, remove_heterogens, keep_water, fix_missing_residues, and fix_terminal_residues. It does not add extra color for every parameter, but the schema already handles those well.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The opening line clearly states the tool's purpose: 'Prepare a PDB file for OpenMM by correcting common structural problems.' This specifies the verb, resource, and intended context. It also distinguishes itself from siblings by placing itself in the workflow between query_pdb_structure/split_pdb and relax_pdb_structure.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Explicit 'WHEN TO USE' section directs the agent to run this after query_pdb_structure and before relax_pdb_structure, and states it is required before relaxation. It also gives decision guidance per parameter, explaining when to adjust chains, pH, heterogen removal, water, and missing-residue modeling.

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

• query_ff_presetsA
  4.7/5.0
  Behavior4/5

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

  With no annotations provided, the description must disclose behavior. It clearly states the return type ('dict mapping preset name → description string'), which is the primary observable behavior. It does not mention side effects or read-only status, but for a listing tool this is minimal and acceptable.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is compact and well-structured: a one-sentence summary, a clear 'WHEN TO USE' section, and a 'Returns' line. Every sentence adds value, and the most important information is front-loaded.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given zero parameters, a declared output schema, and a simple return format, the description is complete. It even includes usage context and a return type description, leaving no critical gaps for the agent to navigate this tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  There are no parameters, so the schema fully covers parameter semantics. The baseline for zero parameters is 4, and the description appropriately does not attempt to add parameter details that don't exist.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('List') and resource ('force-field presets for relax_pdb_structure'), clearly distinguishing it from sibling tools like split_pdb or fix_pdb_structure. It states exactly what the tool does without ambiguity.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The 'WHEN TO USE' section explicitly instructs to call this tool before relax_pdb_structure when unsure about presets or wanting to present options. This provides clear contextual guidance and names the relevant sibling tool, fulfilling the 'when and alternatives' criterion.

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

• set_working_directoryA
  4.7/5.0
  Behavior4/5

  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 a key behavioral trait: the working directory affects all subsequent file I/O and that relative paths resolve against the set path. This is essential context, though it doesn't mention error handling or how to reset the directory, which would make it more complete.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is concise and front-loaded with the core purpose. It uses two sentences plus a brief usage note, with no redundancy or filler. Every sentence contributes actionable information, making it highly efficient.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple tool with one parameter, the description adequately covers purpose, usage, and behavioral impact. The presence of an output schema means return values need not be explained. It is complete for an agent to select and invoke the tool successfully.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema already describes 'path' as an absolute path, but the description adds meaning by explaining that relative paths in other tools resolve against this path. This clarifies the practical role of the parameter beyond the schema's basic type description, enhancing understanding.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's function: 'Set the working directory for all subsequent file I/O.' It uses a specific verb ('set') and resource ('working directory'), and it distinguishes itself from sibling tools by focusing on a configuration action rather than PDB structure operations.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The 'WHEN TO USE' section explicitly instructs when to call the tool: when a user's PDB files are in a specific directory and to avoid writing absolute paths in every call. It also states the consequence (relative paths resolve against `path`), which provides clear guidance on usage.

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

• split_pdbA
  4.7/5.0
  Behavior4/5

  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.

  Conciseness5/5

  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.

  Completeness5/5

  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.

  Parameters4/5

  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.

  Purpose5/5

  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.

  Usage Guidelines5/5

  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.

• relax_pdb_structureA
  4.9/5.0
  Behavior5/5

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

  With no annotations, the description carries the full transparency burden and does so thoroughly. It discloses failure modes (OpenMM will fail on missing atoms/non-standard residues), explains expected energy drops, flags signs of MD divergence, and describes output readiness.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is long but well-structured into clear sections: WHEN TO USE, WORKFLOW POSITION, DECISION GUIDANCE, and OUTPUT. Each paragraph serves a distinct purpose and provides actionable information, so the length is justified for a 20-parameter scientific tool.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's complexity, no annotations, and an output schema, the description covers prerequisites, workflow position, detailed parameter selection, and output validation checks. It gives the agent enough context to invoke the tool correctly and interpret results, making it effectively complete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema covers 100% of parameters, so baseline is 3. The description adds substantial meaning for key parameters like preset, run_md, restrain_backbone, restraint_k, production_steps, and temperature with concrete numeric values and decision rules, elevating it above baseline. It does not discuss every parameter but is not required to given schema coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific action: 'Energy-minimise and optionally run short restrained MD on a prepared PDB.' It clearly identifies the resource (a prepared PDB), the operation (energy minimisation and optional MD), and distinguishes itself as the final pipeline step after fix_pdb_structure.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides explicit WHEN TO USE guidance, positions the tool in the workflow, and warns against passing raw PDBs. It also includes per-preset decision guidance and conditions for setting run_md=False, making alternatives and exclusions clear.

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

• assemble_pdb_structuresA
  5/5.0
  Behavior5/5

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

  With no annotations provided, the description assumes full responsibility for behavioral disclosure. It does so thoroughly: explains chain ID mapping risks after fix_pdb_structure, differentiates handle_conflicts modes with safety implications, and warns that renumbering loses original residue IDs. This goes well beyond basic operation descriptions.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-organized with clear section headers (PURPOSE, WHEN TO USE, WORKFLOW POSITION, DECISION GUIDANCE, OUTPUT). It is information-dense but every sentence serves a purpose, covering essential guidance without wasted words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Despite having 7 parameters and no annotations, the description covers all aspects needed for correct usage: purpose, workflow position, per-parameter decision guidance, and output verification steps. This is a model of completeness for a complex structural biology tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Even though schema coverage is 100%, the description adds significant meaning beyond the schema. For example, it advises when to use chain_id_map, clarifies the practical difference between 'rename' and 'merge', and explains the consequences of renumber_residues and renumber_atoms. This is substantial added value.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states 'Merge multiple PDB files into a single PDB file,' using a specific verb and resource that immediately distinguishes it from siblings like split_pdb. The inverse relationship to split_pdb is implicit, making its purpose unambiguous.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Explicit 'WHEN TO USE' section provides concrete scenarios: after split_pdb + fix_pdb_structure, for building hetero-complexes, and positions itself in the workflow between fix_pdb_structure and relax_pdb_structure. This clearly guides when to choose this tool over alternatives.

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