Server Quality Checklist

Tool Scores

• list_footprintsA
  4.2/5.0
  Behavior4/5

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

  The annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds concrete behavioral context: positions in millimeters relative to board origin, the KiCAD Y-axis convention, and valid layer names. This helps the agent anticipate output semantics without contradicting the annotations.

  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 composed of four informative sentences, each adding value: the listing action, coordinate system, layer filtering, and follow-up usage. It is front-loaded and avoids redundancy with the schema, though slightly longer than strictly necessary.

  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 tool has an output schema, so return format details are not required. The description covers the essential behavior, coordinates, layer filtering, and downstream usage, making it complete for a read-only listing tool.

  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% – the filter_layer parameter's description already includes the valid layer values. The tool description does not add new meaning specific to the parameter beyond reinforcing the optional filter and the fact that omitting it lists all layers, so a baseline score of 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 'Lists all footprints (components) on the PCB board' – a specific verb and resource – and enumerates the exact attributes (positions, rotation angles, layers, pad counts). This clearly differentiates it from sibling tools like list_nets and list_tracks.

  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?

  It provides context by stating the optional layer filter and lists valid layer values, plus explains how to use returned reference designators in follow-up tool calls. However, it does not explicitly state when not to use it or name an alternative like get_footprint for single-component details.

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

• get_footprintA
  4.4/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint and destructiveHint; the description adds context by detailing specific returned data (position, rotation, pads, net names) and error behavior (lists available references). No contradictions with annotations.

  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?

  Four sentences with clear structure: purpose, contents, usage, error behavior. Each sentence adds value, though slightly more verbose than strictly necessary.

  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?

  With output schema present and read-only annotations, the description fully explains the return values and error handling. Complete for a simple read-only tool.

  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% with examples and a pointer to list_footprints. The description only repeats 'reference designator' without adding meaning beyond what the schema already provides.

  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?

  Clearly states 'Returns detailed information about a single footprint' with a specific verb and resource, distinguishing it from list_footprints (which lists all) and edit_footprint (which modifies).

  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?

  Provides explicit guidance: 'Use this when you need to understand a specific component's connectivity or physical dimensions.' Does not name alternative tools directly, but the error behavior hints at discovering references.

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

• edit_footprintA
  4.5/5.0
  Behavior5/5

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

  Beyond the destructiveHint annotation, the description adds crucial behavioral details: 'This creates one undo step: Ctrl+Z reverts the edit,' 'dry_run=true to preview the change without applying it,' and a specific warning that 'set_layer flips the component, which may affect routing.' These disclosures significantly inform the agent about side effects and safety.

  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 yet information-dense: a one-sentence overview, bullet-like action breakdown, undo behavior, dry-run tip, and warning. Every sentence earns its place, and the structure naturally front-loads the core purpose before caveats.

  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?

  With an output schema present and a complex 6-parameter tool, the description fully covers the operation's scope, prerequisites per action, preview mode, undo behavior, and side effects. No critical behavioral gaps remain; the agent can confidently invoke the tool for any listed action.

  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 schema already provides 100% parameter coverage, including required-when conditions and example field names. The description restates these requirements ('set_field requires field_name and field_value') and adds a routing warning, but does not add substantial new parameter-level semantics beyond what the schema supplies. Thus 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 clearly states the tool edits a footprint's properties and enumerates specific actions (set_field, set_layer, lock, unlock) with distinct purposes. This distinguishes it from sibling tools like list_footprints (read-only) and move_footprint (position change) by emphasizing property/layer/lock edits.

  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 provides clear context for when to use each action (e.g., 'set_field sets a named field (requires field_name and field_value)') and includes practical guidance like using dry_run=true to preview. However, it does not explicitly contrast with alternatives like move_footprint or get_footprint, so exclusions are not stated.

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

• get_board_infoA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds meaningful context by specifying the prerequisite (KiCAD running with a board open in the PCB editor) and detailing exactly what information is returned, which goes beyond the bare annotation.

  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 front-loaded with the primary action ('Returns...') and uses four concise sentences, each adding value: the return statement, the detailed list of returned data, the timing guidance, and the environmental prerequisite. There is no filler or redundancy.

  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 presence of an output schema and zero parameters, the description needs only to cover purpose, usage timing, and prerequisites—all of which are present. It fully equips an agent to understand what the tool does, when to call it, and what is needed for successful invocation.

  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 tool has zero parameters, so there is nothing to explain. With an empty schema and no parameters, the description does not need to elaborate on input semantics; the baseline of 4 for zero parameters applies.

  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 explicitly states the tool 'Returns high-level information about the currently open PCB board in KiCAD' with a specific verb and resource. It lists concrete data fields (filename, dimensions, layer count, counts of footprints/tracks/vias/zones/nets), which clearly distinguishes it from siblings that focus on individual board elements.

  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?

  It provides clear context for when to use the tool: 'This is typically the first tool to call when starting work on a board.' It does not explicitly name alternatives or exclusions, but the positioning as the initial overview step implicitly differentiates it from more specific tools like list_footprints or list_tracks.

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

• get_board_statsA
  4.5/5.0
  Behavior4/5

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

  Annotations already mark the tool as read-only and non-destructive. The description adds interpretive context about what the stats mean, such as zero unrouted nets indicating a fully routed board, which helps the agent understand the output's significance.

  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?

  Three sentences, front-loaded with the core function, followed by practical usage guidance. No redundant wording.

  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 and the presence of an output schema, the description sufficiently covers what the tool returns and how to interpret it. It also provides enough context to differentiate from sibling tools.

  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?

  With zero parameters, the schema covers all requirements. The description adds no parameter-specific information, but none is needed.

  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 returns aggregate board statistics, enumerating the specific metrics (dimensions, track length, via count, zone count, unrouted nets). This distinguishes it from sibling tools like get_board_info and list_zones, which serve different purposes.

  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 explicitly advises using the tool for a quick summary of routing completeness and suggests comparing track length across iterations. It does not name alternative tools for when not to use it, but the context is clear.

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

• get_net_connectionsA
  4.5/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral details beyond that: a 50-entry cap with a truncation note, and that non-existent nets return an error listing available nets. This provides useful expectations about tool behavior without contradicting annotations.

  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 yet information-dense: main action, what is returned, purpose, cap/truncation behavior, and error handling. Every sentence serves a purpose and the structure is front-loaded with the primary function.

  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 (not shown but present), the description already summarizes the returned fields (reference designator, pad number, pad position). It covers truncation, error paths, and typical use cases. For a tool with a single parameter, this is fully complete for an agent to invoke it correctly.

  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%, with the net_name parameter well-documented (case-sensitive, examples, cross-reference to list_nets). The tool description adds little about the parameter itself, but the schema carries the weight, so a baseline of 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 uses a specific verb ('Returns') and resource ('footprint pads connected to a given net'), clearly distinguishing it from siblings like list_nets and list_tracks. It also states the purpose: showing which components are electrically linked through the net, and how it maps to PCB connectivity.

  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 provides clear context for when to use the tool: 'useful for understanding schematic connectivity as realized on the PCB, or for tracing signal paths between components.' It does not explicitly name alternatives or exclusion scenarios, but the use case is well-clarified.

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

• list_netsA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds behavioral context by explaining what the tool returns (pad counts, track segments) and why certain nets like GND/VCC have higher counts. This goes beyond the annotation's binary safety flags and helps predict the tool's behavior, though it stops short of discussing pagination or performance.

  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 three sentences, each earning its place: the first defines the core action and output, the second provides essential background on what nets are, and the third gives actionable next steps. It is informative without being verbose, and it front-loads the main purpose.

  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 this is a simple read-only listing tool with an output schema available, the description fully supports an agent in understanding when to call it and how to use the results. It mentions the key output fields (nets with pad counts and track segments) and directs to related tools for deeper exploration. No important gaps remain.

  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 tool has zero parameters, so the input schema is fully covered by its empty properties object. The description does not need to explain parameters, but it does explain the meaning of the returned net names, which adds semantic value for downstream use. This meets the baseline for zero-parameter tools.

  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 ('Lists') and resource ('all electrical nets on the PCB board') and clearly states the output includes pad counts and track segments. This distinguishes it from sibling tools like list_tracks and list_zones, which focus on different PCB elements.

  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 provides concrete follow-up guidance, telling the user to use returned net names in get_net_connections or list_tracks to explore connectivity. It does not explicitly exclude alternatives or state when not to use this tool, but the context of listing all nets is clear enough for an agent to select it appropriately.

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

• list_tracksA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is established. The description adds useful behavioral context: 'Results are capped at 50 entries' and valid layer values. There is a minor inconsistency between 'Lists all' and the cap, but the cap is disclosed, so transparency is preserved.

  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 four sentences, front-loaded with the primary purpose, followed by output details and filter options. Every sentence contributes useful information without repetition or fluff.

  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?

  With an output schema present and annotations covering safety, the description is complete: it states what the tool does, what fields are returned, how filters work, the result cap, and valid layer values. This is sufficient for an agent to select and invoke the 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?

  Schema coverage is 100% and both parameters have full descriptions. The description adds the key semantic that 'Both filters can be combined', which is not explicitly in the schema. It also re-emphasizes valid layer values and the optional nature of filters, providing extra clarity beyond the schema.

  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 'Lists all track segments (copper traces) on the PCB board', providing a specific verb and resource. It clearly distinguishes from siblings like list_zones and list_footprints by focusing on copper traces and enumerating their attributes (positions, width, layer, net).

  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 gives clear context on when to use filters: 'Optionally filter by net name... or by layer... Both filters can be combined.' It does not explicitly name alternative tools, but the usage context is clear and the cap of 50 results is stated. The schema for net_name references list_nets, which partially compensates.

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

• list_zonesA
  4.5/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it explains that unfilled zones do not electrically connect until a refill is run, which goes beyond the raw annotation fields. This enriches the agent's understanding of the domain.

  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 four sentences long, front-loaded with the core listing purpose, and every subsequent sentence earns its place by explaining zone terminology and fill behavior. There is no redundancy or padding.

  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 zero-parameter listing tool with an output schema and strong annotations, the description fully covers the domain concepts needed to interpret the results. It explains what zones are, what the fill status means, and the operational implication of unfilled zones. No significant gaps remain.

  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 zero parameters, so the schema provides no burden. The baseline for 0 parameters is 4, and the description adds semantic detail about the returned data (net, layer, bbox, fill status), making the tool's output expectations clear.

  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 the specific verb 'Lists' and identifies the exact resource ('all copper zones on the PCB board'), then enumerates the key attributes returned (net, layer, bounding box, fill status). This clearly distinguishes it from sibling tools like list_footprints, list_nets, and list_tracks.

  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 provides clear context about when zones are relevant (ground planes, power distribution) and explains the semantic difference between filled and unfilled zones, implying when this tool is useful. However, it does not explicitly name alternative tools (e.g., manage_zone for modifications) or state when not to use it, stopping short of a 5.

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

• create_trackA
  4.7/5.0
  Behavior5/5

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

  Beyond the destructiveHint annotation, the description discloses undo behavior, dry-run preview, and consequences of invalid nets. This significantly enhances transparency and does not contradict annotations.

  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 but information-dense, with every sentence contributing (purpose, segment logic, prerequisite, undo, preview, warning). It is well-structured and 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 the tool's complexity, the description covers creation mechanism, constraints, side effects, and preview option. Output schema exists, so detailed return value explanation is unnecessary; the description is complete for safe and correct use.

  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%, setting a baseline of 3. The description adds value by explaining that each consecutive point pair becomes a straight segment, which is not fully conveyed by the schema's 'Path points' description.

  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 ('Creates a copper track (trace)') and resource (track on a board with path of 2+ points). It distinguishes the tool from siblings like create_via and manage_zone by focusing on track creation and net/layer assignment.

  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?

  Provides clear context such as net existence requirement, dry_run preview, and DRC warning. It lacks explicit alternative tool recommendations or exclusions, but the usage hints are sufficient for practical invocation.

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

• create_viaA
  4.7/5.0
  Behavior5/5

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

  Annotations declare destructiveHint=true, and the description adds critical context: it creates one undo step (Ctrl+Z), warns that it modifies the board, and explains that defaults are used when parameters are omitted. The dry_run option is also disclosed, going beyond the annotation's bare boolean.

  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?

  Every sentence contributes: core operation, layer connectivity, defaults, undo behavior, dry-run, and a warning. The structure is front-loaded and compact without unnecessary filler.

  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 output schema exists and the description covers side effects, warnings, defaults, and preview mode, the tool is fully contextualized. No gaps remain for an agent to understand what happens and what to expect.

  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% with detailed parameter descriptions. The description adds value by explaining default design-rule behavior when diameter/drill are omitted and by explicitly recommending dry_run=true for preview, which is not fully captured in the schema alone.

  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 'Places a via' at a specified position, defines it as a vertical connection between copper layers, and mentions net assignment. This specific verb+resource statement distinguishes it from sibling tools like create_track or manage_zone.

  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 intended use is implied by 'Places a via...' and reinforced with 'Place vias only where connectivity is needed.' It does not explicitly name alternatives or when-not conditions, but the scenario is clear. The dry-run tip provides a safe preview path.

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

• get_design_rulesA
  4.7/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the read-only nature is covered. The description adds valuable behavioral context: KiCAD 10.x extraction source, 'not configured' defaults falling back to internal defaults, and that the values represent manufacturing limits. This goes beyond the annotations and enriches understanding.

  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?

  Three sentences, each earning its place: the first states the core purpose and outputs, the second explains context (KiCAD version and defaults), and the third gives a usage directive. No redundant wording; front-loaded with the main action.

  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 tool has no parameters and an output schema, so the description doesn't need to detail return types. It covers the key contextual aspects: what the rules are, where they come from on KiCAD 10.x, fallback behavior for unset values, and when to invoke the tool—making it complete for a read-only query.

  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 tool has zero parameters and 100% schema coverage (empty schema), so parameter semantics are trivially satisfied. The description does not need to explain parameters, but it adds clarity about the output (returning specific millimeter values), which aligns with baseline 4 for a no-parameter tool.

  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 'Returns' and names the exact resource: the board's design rules derived from the Default netclass, listing the specific dimensions (clearance, track width, via drill, via pad). It clearly distinguishes itself from siblings by noting it's for reading rules, not creating tracks/vias or listing zones.

  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?

  Explicitly states when to use: 'Use this before creating tracks or vias to know valid minimum dimensions.' This provides a clear use case and implies the tool is a prerequisite for creation tools like create_track and create_via, giving strong contextual guidance without needing to name alternatives.

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

• move_footprintA
  4.8/5.0
  Behavior5/5

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

  Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description adds: the move creates one undo step (Ctrl+Z in KiCAD), modifies the board (WARNING), child pads follow automatically, and dry_run preview shows current position, target position, and delta. This enriches the destructive behavior with actionable details.

  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 moderately long but every sentence adds value: action, identification, coordinate system, undo behavior, dry-run purpose, warning, and child-pad behavior. It is well-structured and front-loaded with the core purpose.

  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 (positioning, rotation, dry-run, undo, destructive nature), the description covers all critical aspects: how to identify the footprint, coordinate units and direction, preview capability, undo step, and consequences. The output schema exists, so return-format details are not required in the description. No gaps.

  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 the schema already covers 100% of parameters, the description adds semantics: 'mm relative to board origin', 'Y increases toward bottom of the board', 'reference designator examples', 'dry_run=true shows current/target/delta', and 'rotation omit keeps current rotation'. This significantly aids correct invocation beyond raw schema.

  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 starts with a specific verb and resource: 'Moves a footprint (component) to a new position on the board and optionally changes its rotation angle.' It clearly identifies the footprint via reference designator and distinguishes this from sibling tools like edit_footprint by focusing on positional/rotation changes.

  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 provides clear usage context: positions are in millimeters from board origin, Y axis direction follows KiCAD convention, and dry_run should be used to preview changes. It also directs users to list_footprints to discover available references. While it doesn't explicitly state when not to use this tool versus edit_footprint, the positional focus and dry-run guidance are clear.

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

• manage_zoneA
  4.9/5.0
  Behavior5/5

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

  Even though annotations already indicate destructiveHint, the description adds deeper behavioral context: it warns that the board is modified, notes that deletion removes copper fill, mentions undo behavior (Ctrl+Z per action), and explains the dry_run option. These details go well beyond the annotation flags and fully inform the user of consequences.

  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 tightly structured: opening overview, per-action detail, prerequisites, undo, dry run, and a final warning. Every sentence conveys necessary information without fluff, and the front-loaded verb makes the purpose immediately clear. It is appropriately sized for the tool's complexity.

  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 all essential aspects: actions, parameter requirements, performance note for refill, undo behavior, dry-run preview, and explicit destruction warning. It also integrates the dependency on list_zones for IDs. With an output schema present, the lack of return-value detail is acceptable, making this complete for the tool's complexity.

  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 value by grouping parameters by action (e.g., 'net and layer' for create, 'zone_id' from list_zones for delete), and clarifies the closed-polygon requirement. While much of this mirrors the schema, the action-oriented organization helps the agent quickly map parameters to usage.

  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 three-part verb phrase ('Creates, refills, or deletes a copper zone on the board'), clearly identifying the resource and distinguishing it from sibling tools like list_zones. It goes further by enumerating each action with precise behavior, leaving no ambiguity about what the tool does.

  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 guidance on when to use each action and mentions required prerequisites (e.g., 'at least 3 outline points forming a closed polygon'). It also points to the sibling tool 'list_zones' for obtaining IDs, and recommends using 'dry_run=true' to preview actions, effectively contrasting safe and destructive usage.

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