Server Quality Checklist

Tool Scores

• openroad_placeB
  3.4/5.0
  Behavior2/5

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

  There are no annotations, so the description carries the full burden of disclosing side effects, safety, and preconditions. It only restates the placement operation and says nothing about whether the input DEF is modified, whether an output file is written, or what failure conditions exist. This is a significant transparency gap for a transformation tool.

  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?

  A single front-loaded sentence that states the verb, scope, and target file type in one pass. There is no repetition of schema fields and no filler, making it highly concise and efficient.

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

  Completeness2/5

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

  With six parameters, no annotations, and no output schema, the description should explain prerequisites, side effects, and expected results. It only covers the transformation itself, leaving the agent to guess about flow order and what the tool returns or writes.

  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 description coverage is 100%, so the baseline is 3. The description adds general context about the placement operation but does not elaborate on parameters like density or output_def beyond their schema descriptions.

  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 ('Performs'), names the resource ('standard cell ... placement'), and distinguishes the step by naming both global analytical placement (RePLace) and legalized detailed placement (DPL). This clearly differentiates it from sibling floorplan, route, and STA tools.

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

  Usage Guidelines3/5

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

  The placement step is implied by the operation and the sibling tool names, but the description never explicitly states when to use this tool versus openroad_floorplan, openroad_route, or openroad_pnr, nor does it mention prerequisites. An agent can infer usage context only from the tool name and flow terminology.

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

• openroad_floorplanA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description must carry behavioral disclosure. It does communicate the main side effect—generating a floorplan DEF file via OpenROAD—but does not disclose overwrite behavior for an existing output_def, execution characteristics, or failure modes. This is adequate but has clear transparency gaps.

  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?

  One focused sentence with no filler; the primary action and output artifact are front-loaded. Every phrase carries information.

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

  Completeness3/5

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

  The description is sufficient for a simple floorplan initialization step, but with no output schema or annotations it leaves out useful operational context: whether existing DEF files are overwritten, what the tool returns on success, and how this step sequences into the sibling P&R tools.

  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 description coverage is 100%, so the baseline is 3. The description adds only conceptual grouping ('core/die sizing', 'I/O pin placement') that maps loosely to die_width, die_height, and core_margin, but no new parameter-level meaning.

  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 ('Initializes') and a concrete resource: ASIC floorplan boundaries, core/die sizing, and I/O pin placement. It also names the deliverable, a floorplan DEF file, which separates it from the place/route/STA sibling tools even without naming them explicitly.

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

  Usage Guidelines3/5

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

  The description never states when to run this tool versus openroad_place, openroad_route, or openroad_pnr. It implies the floorplan step from the 'floorplan' terminology and DEF output, but leaves workflow ordering and alternative selection to inference.

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

• openroad_routeA
  3.7/5.0
  Behavior3/5

  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 the core behavior (routing and reporting metrics) but does not mention side effects like writing the output DEF, output format details, or error behavior. Some transparency is present, but significant gaps remain.

  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?

  A single sentence that states the core action, the algorithm, the input, and the outputs without any fluff. Information is front-loaded and easy to parse.

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

  Completeness3/5

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

  With no output schema and no annotations, the description should explain what the agent can expect in return. While it mentions reporting metrics, it does not specify the output format or whether files are written. For a 5-param tool in a suite, this is adequate but not fully 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 description coverage is 100%, so the schema already documents all parameters. The description adds contextual value by clarifying that routing operates on a placed DEF and reports metrics, but it does not add detail beyond the schema for individual parameters.

  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 a specific action: performing global routing (FastRoute) and detailed routing on a placed DEF file. It also names the resource and the reported outcomes (wirelength and DRC metrics), which distinguishes it from sibling tools like openroad_place and openroad_sta.

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

  Usage Guidelines3/5

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

  The phrase 'placed DEF file' implies the tool is used after placement, but there is no explicit guidance about when to choose this tool over siblings such as openroad_pnr or openroad_place. No alternatives or exclusions are mentioned.

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

• openroad_staA
  3.9/5.0
  Behavior3/5

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

  With no annotations present, the description carries the full burden of behavioral disclosure. It does reveal the core behavior—running OpenSTA and reporting timing metrics—but does not mention side effects, whether it is strictly read-only, how constraints are derived when sdc_file is absent, or the exact form of the report. This is adequate but leaves meaningful gaps.

  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 a single front-loaded sentence with no filler. It packs the tool's purpose, input phase, engine, and key outputs into a compact form that is easy to parse quickly.

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

  Completeness3/5

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

  The description covers the essential purpose and outputs, but given no annotations and no output schema, it should provide a bit more context. Notably absent is guidance on how sdc_file and clock_period_ns interact, whether the tool writes any files, and what the returned report looks like. The schema covers parameters well, but the overall invocation context is only minimally 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 description coverage is 100%, so baseline is 3. The tool description repeats the placed/routed DEF detail already present in the def_file schema description and adds no new meaning for top_module, sdc_file, clock_period_ns, cwd, or timeout_ms. It neither harms nor meaningfully enhances parameter 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 a specific verb ('Performs'), resource ('placed or routed DEF files'), and engine ('OpenSTA'), and lists concrete outputs (WNS, TNS, critical paths). This makes it easy to distinguish from sibling flow tools like openroad_place, openroad_route, and openroad_floorplan.

  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 description establishes the correct context: this tool is for static timing analysis on placed or routed DEF files, implying it is used after placement/routing rather than at floorplan time. It does not explicitly name alternatives or say when not to use the tool, but the usage context is clear.

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

• openroad_toolchain_infoA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral disclosure burden. It clearly signals a read-only, side-effect-free operation by saying 'Returns ... information'. It also specifies the scope of what is returned, which is sufficient for a simple info tool, though it does not detail output structure or error behavior.

  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 a single, well-structured sentence that front-loads the action and clearly lists the information domains. There is no redundant wording or unnecessary detail.

  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, optional-parameter info tool, the description provides enough context: it states what is returned and for which components. There is no output schema, so a slightly more explicit note about the exact return shape would improve completeness, but the current description is adequate for an agent to decide to invoke it.

  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?

  The only parameter, cwd, is already fully described in the schema as 'Optional workspace directory', so schema coverage is 100%. The tool description adds no additional meaning about how cwd affects the returned information, but the schema already provides adequate semantics for this optional 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 uses a specific verb ('Returns') and names the exact resource: runtime and version information for OpenROAD, OpenSTA, and supported PDKs. This clearly distinguishes it from the sibling execution tools like openroad_pnr and openroad_sta, which perform operations rather than reporting environment info.

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

  Usage Guidelines3/5

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

  The description implies the tool is for checking the active toolchain environment, but it does not explicitly state when to use it versus siblings or when not to use it. An agent can infer usage from the info-returning nature, but there is no direct guidance or exclusion.

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

• openroad_pnrA
  4.1/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden. It discloses that this is a multi-stage automated flow, that it runs on OpenROAD, and that it returns area, utilization, wirelength, and timing slack metrics. It also implies mutation/creation of files, but does not mention whether inputs are modified, how long it can take, or whether it writes intermediate files beyond the optional DEF. It is fairly transparent but could disclose time cost and side effects more explicitly.

  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?

  One compact, front-loaded sentence that lists the stages, the input type, the tool, and the outputs. It earns its place with useful metrics. Minor issue: it crams many stages into a parenthetical, which could be slightly easier to parse, but overall it's efficient.

  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 complex 8-parameter tool with no output schema, the description gives a strong high-level picture, names required inputs (gate-level netlist, top module) implicitly, and lists return metrics. It lacks details on side effects, runtime expectations, and whether it uses SDC or clock period, but the schema fills parameter gaps and the sibling list provides alternative-stage context. Mostly complete, with minor gaps.

  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 description coverage is 100%, so the baseline is 3. The description does not add semantics beyond the schema because it only summarizes the overall flow and outputs, not the individual parameters like netlist_file, top_module, or core_utilization. The schema already documents each parameter 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 description is a specific verb+resource statement: it performs end-to-end automated digital ASIC physical design (floorplanning, placement, routing, and static timing analysis) on a gate-level netlist using OpenROAD, and names the exact metrics returned (area, utilization, wirelength, timing slack). This clearly distinguishes it from the sibling tools, which each handle a narrower stage (floorplan, place, route, sta).

  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 description implies the tool is for full physical design flow and returns metrics, and the sibling list makes alternatives explicit. However, it does not explicitly state when to use this end-to-end tool versus calling the individual stages (openroad_floorplan/openroad_place/openroad_route/openroad_sta). The guidance is clear contextually but lacks a direct 'use this instead of...' statement.

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