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

No annotations are provided. The description does not disclose side effects, coordinate system details (e.g., bottom-left and top-right corners), or whether it modifies an existing layout. The units 'micrometers' are mentioned but insufficient for behavioral understanding.

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

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

The description is a single sentence, which makes it concise, but it sacrifices necessary detail. It is appropriately front-loaded but lacks structure (e.g., no bullet points or parameter breakdown).

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

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

With 6 parameters, no schema descriptions, and an output schema present (content unknown), the description is insufficient. Missing information on return value, error cases, and the relationship between coordinates (e.g., x1,y1 and x2,y2 as opposite corners) makes it incomplete for correct invocation.

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

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

Schema description coverage is 0%, so the description must explain parameters. It only mentions 'rectangle (micrometers)' and 'layer/datatype', but fails to explain what x1,y1,x2,y2 represent (e.g., coordinates, corners). The default datatype=0 is not hinted.

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

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

The description specifies the verb 'Add', the resource 'rectangle (micrometers)', and the context 'on GDS layer/datatype'. It clearly distinguishes from sibling tools like add_polygon or add_label, indicating it's for rectangles.

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

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

No guidance on when to use this tool versus alternatives. For example, it doesn't explain when to use add_box instead of add_polygon for rectangles, or mention prerequisites like an open layout.

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

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

No annotations provided; description does not disclose side effects, permissions, or output characteristics. The presence of an output schema is not mentioned, so the agent gains no behavioral insight beyond the action.

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

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

Single sentence is concise and front-loaded with the action. It could be slightly expanded without losing conciseness to cover additional parameters.

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

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

With 5 parameters, a non-empty output schema, and nine sibling tools, the minimal description leaves significant gaps: no return value description, no parameter details beyond x,y,text, and no differentiation from similar tools.

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

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

Schema description coverage is 0%, and the description partially compensates by specifying units for x and y ('micrometers') and mentioning the 'text' parameter. However, layer and datatype are not explained, and the description does not cover all parameters.

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

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

The description clearly states the action 'Add' and the object 'text label' with coordinate units. It distinguishes from geometry tools like add_box but could be more explicit about being a text label versus other annotation tools.

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

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

No guidance on when to use this tool versus siblings like add_box, add_path, or add_polygon. Context for appropriate use cases is missing.

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

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

With no annotations, the description carries full disclosure burden. It only states the basic action and unit (micrometers) but does not disclose side effects, such as whether existing paths are overwritten or appended, or any authorization requirements.

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

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

The description is a single, front-loaded sentence with no waste. However, it partially restates the tool name without adding significant new information beyond parameter specifics.

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

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

Given 4 parameters and no schema descriptions, the description should provide more complete coverage. It explains two parameters but omits 'layer' and 'datatype', and does not mention the output schema or behavior for missing optional parameters.

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

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

The description adds meaning for 'points' (centerline [x,y] in micrometers) and 'width', but fails to explain 'layer' and 'datatype' parameters. With 0% schema coverage, the description compensates only partially.

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

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

The description clearly states the action ('Add a path') and specifies the resource is a path defined by centerline points and width. It implicitly distinguishes from sibling tools like add_box or add_polygon by describing a path-specific structure.

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

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

No guidance is provided on when to use this tool versus alternatives (e.g., add_polygon for filled shapes) or any prerequisites. The description lacks context for appropriate usage.

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

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

With no annotations and no description of behavioral traits (e.g., destructive actions, permissions, or side effects), the agent lacks critical context beyond the basic operation. The description does not disclose any constraints or effects.

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

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

The description is a single sentence with no wasted words, making it concise. However, it could be slightly more structured to include parameter details without sacrificing brevity.

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

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

Given the absence of annotations, low schema coverage, and no mention of output despite having an output schema, the description leaves significant gaps. An agent would lack sufficient context to use the tool reliably without external knowledge.

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

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

Schema coverage is 0%, so the description must add meaning. It explains 'points' as vertices in [x, y] format, but does not describe 'layer' or 'datatype' parameters, leaving their semantics unclear.

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

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

The description uses a specific verb 'Add' and resource 'polygon', clearly stating the input format as a list of [x, y] vertices in micrometers. This distinguishes it from sibling tools like add_box or add_path which create different shapes.

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

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

No guidance is provided on when to use this tool versus alternatives, nor any prerequisites or context. The description only states the action, leaving the agent to infer appropriate usage.

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

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

No annotations are provided, so the description takes on the burden of behavioral transparency. It explains the geometry but does not disclose side effects, authorization needs, or whether it modifies existing layout.

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

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

The description is concise (two sentences), front-loads the main action, and adds detail without superfluous text.

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

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

The description covers key parameters and behavior, but does not mention the tool's return value or output, which could be useful given 13 parameters.

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

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

With 0% schema description coverage, the description adds significant meaning by explaining the array structure and enclosure, though it omits datatype parameters.

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

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

The description clearly states the tool creates a via (cut array with enclosing metal) at a given coordinate, differentiating it from siblings that add other shapes or perform different operations.

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

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

The description implies usage for creating vias, but does not explicitly state when to use this tool over alternatives or provide exclusions.

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

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

With no annotations, the description carries the full burden. It explains routing behavior (L-corners, horizontal_first parameter), via insertion for layer changes, and unit (um). Does not mention destructive effects, but as a creation tool, this is expected.

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

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

Three sentences, no fluff, front-loaded with core purpose. Every sentence adds value: wire type, routing algorithm, parameter meaning, and via guidance.

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

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

Given output schema exists, description need not cover return values. Covers essential aspects: wire geometry, parameters, and layer change hint. Missing constraints (min width, layer limits) are likely in schema.

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

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

Schema coverage is 0%, so description is crucial. It explains points (routes through points), horizontal_first (corner direction), and hints at via usage. Layer and width are not detailed, but their meaning is intuitive for a wire tool. Adds significant value beyond the schema.

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

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

The description clearly states the tool adds a 'Manhattan wire' with axis-aligned segments, distinguishing it from siblings like add_path (arbitrary polylines) and add_box (rectangle). The verb 'add' and resource 'wire' are specific.

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

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

Implies usage for orthogonal routing ('Manhattan wire', 'axis-aligned'). Mentions that for layer changes, users should drop an add_via, guiding on when to use alternative tools. Does not explicitly compare with add_path, but context provides differentiation.

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

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

Discloses that subsequent draw calls go into this cell and that use_cell returns to top. Lacks detail on whether existing cells are selected or new cells created, but overall covers key behaviors.

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

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

Two concise sentences with no wasted words. Front-loaded with purpose and immediate usage context.

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

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

Adequate for a simple tool with one parameter. Does not explain return value or error conditions, but the workflow context is well covered.

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

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

The only parameter 'name' is explained by 'create (or select) a cell', adding meaning beyond the schema. Could be more explicit but sufficient.

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

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

Description clearly states the tool creates or selects a cell and makes it the active drawing target. It distinguishes from sibling drawing primitives by specifying it sets the context for subsequent shapes.

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

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

Explicitly describes workflow: use this to build a library cell, then use_cell and place_cell. Provides clear instructions on when and how to use, including returning to top cell.

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

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

With no annotations, the description fully describes the tool's behavior: it runs DRC rules, reports violations per rule, and limits output via max_report. It details five rule types with their dictionaries. It does not mention error handling or performance, but the core behavior is well-covered.

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

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

The description is structured with a summary sentence followed by detailed rule specifications. It is somewhat lengthy but every part provides necessary information. It could be slightly more concise, but the structure is logical and easy to follow.

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

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

Given no annotations but a known output schema, the description covers purpose, parameters, and rule types comprehensively. It does not detail return format (likely covered by output schema) or error states, but for a DRC check tool it is sufficiently complete for an agent to use effectively.

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

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

Schema coverage is 0%, so the description must compensate. It thoroughly explains the 'rules' parameter with example dicts and meanings for all five rule types. It clarifies 'path' (optional, current session if absent) and 'max_report' (violation limit). 'top_cell' is not explained beyond its name, but the overall parameter explanation adds significant value.

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

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

The description starts with 'Run simple DRC rules against a layout and report violations,' which clearly states the action (run DRC rules), target (layout), and output (violations). It is distinct from sibling tools that deal with editing or inspecting GDS files, making the purpose unambiguous.

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

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

The description mentions it operates on a given path or the current session, providing context for when to use the tool. It does not explicitly state when not to use it or list alternatives, but the context of DRC checking versus other layout operations is clear enough.

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

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

With no annotations, the description carries full burden. It discloses that areas use merged geometry (no double-counting) and coordinates are in micrometers. It also states the behavior regarding session modification.

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

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

The description is concise (two sentences) and front-loaded with the main purpose. However, it could be more structured (e.g., bullet points) for easier parsing.

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

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

Given the output schema exists, return values are covered. The description lists key outputs. However, missing explanation of the 'top_cell' parameter reduces completeness for a simple two-parameter tool.

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

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

Schema coverage is 0%, so description must compensate. It partially explains the 'path' parameter (inspect file vs session) but lacks format details. The 'top_cell' parameter is not explained at all, leaving a significant gap.

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

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

The description clearly states the tool inspects a layout and lists specific outputs (per-layer shape count, area, bbox, cell list). It uses specific verbs and distinguishes from siblings like load_gds and layout_info.

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

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

The description explains when to use with path (inspect file without touching session) vs without (inspect current session). It provides clear context but does not explicitly mention when not to use or alternatives.

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

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

Without annotations, the description carries the transparency burden. It lists output fields, which is helpful, but does not disclose whether the tool is read-only, potential failure modes, or state dependencies.

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

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

The description is a single, front-loaded sentence with no extraneous words. Every word adds value.

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

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

Given the tool has no parameters and an output schema exists, the description covers the return fields. However, it omits context such as requiring an open layout, which could improve completeness.

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

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

There are zero parameters, and schema coverage is 100%. The description adds no parameter info, but the baseline for 0 parameters is 4, and the description does not detract.

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

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

The description clearly states the tool's function, listing specific fields reported (top cell, dbu, layers, bbox, shape count). This distinguishes it from sibling tools that modify layouts.

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

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

The description lacks explicit guidance on when to use this tool versus alternatives. It implies it retrieves current layout state but does not mention prerequisites like an open layout or contrast with other tools.

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

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

With no annotations, the description carries the full burden. It discloses that loading replaces any current in-memory layout, which is a critical destructive behavior. It also explains the default behavior of top_cell. No contradictions with annotations (none provided).

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

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

The description is concise, front-loaded with the main action, and each sentence adds value. No unnecessary words. It efficiently conveys the purpose, workflow, and key parameter behavior.

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

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

For a simple load tool with two parameters and an output schema present, the description covers purpose, workflow, key behavior, and parameter defaults. It could mention that the layout is now in memory for subsequent edits, but the workflow hint covers that. Overall complete for the context.

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

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

Schema coverage is 0%, so the description must compensate. It explains that path is the file to load and top_cell selects the cell to edit with a default. This adds some value but lacks details on path format, file existence checks, or error handling. With only two parameters, minimal coverage is acceptable.

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

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

The description clearly states the tool loads an existing GDS/OASIS file into the active session for editing. It uses a specific verb (load) and resource (GDS/OASIS file), and distinguishes itself from siblings like new_layout and save_gds by describing its role in the editing workflow.

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

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

The description provides clear context for when to use the tool, describing the workflow of loading, editing, then saving. It implicitly distinguishes from new_layout (for creating new layouts). However, it could explicitly state that this tool should be used when editing existing files, not for creating new ones.

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

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

With no annotations, the description carries full burden. It discloses the destructive 'reset' behavior, but does not elaborate on side effects (e.g., data loss) or prerequisites. Some key behaviors are implied but not fully transparent.

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

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

The description is two sentences plus parameter explanations, all front-loaded and without fluff. Every sentence provides essential information.

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

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

For a simple initialization tool with output schema (not needing return value docs), the description covers reset behavior and parameter details. Minor gap: no mention of the state previous to reset or post-creation effects.

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

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

Schema coverage is 0%, so description compensates by explaining top_cell and dbu with units and a default example. This adds meaning beyond the schema's bare titles and defaults.

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

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

The description clearly states the verb 'Start' and resource 'new in-memory layout'. It distinguishes from sibling tools like open_layout by implying this creates a fresh layout, not opening existing. The purpose is specific and unambiguous.

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

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

The description mentions 'Resets any previous in-memory layout', which implies a fresh start, but does not explicitly state when to use this vs open_layout. No explicit alternatives or when-not conditions are given.

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

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

Reveals editor mode and the effect of providing a file vs not. Lacks details on permissions, blocking behavior, or return values. With no annotations, description carries burden but is minimally adequate.

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

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

Two sentences, front-loaded with key information, no unnecessary words. Each sentence adds value.

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

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

For a tool with one optional parameter and an output schema, the description covers essential use cases. Missing details on side effects or the fact that it launches KLayout, but name and context suffice.

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

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

Despite 0% schema description coverage, the explanation of file_path's optionality and effect (edit vs create blank) adds meaning beyond the schema. Does not specify format or path conventions but schema is simple.

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

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

Description clearly states the verb 'open' and resource 'KLayout in editor mode', and distinguishes between editing a file vs creating a blank layout. It differentiates from sibling 'open_layout' by specifying editor mode.

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

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

Provides clear usage context: with a file to edit it, without for a blank layout. Does not explicitly state when not to use or mention alternatives, but the context is sufficient.

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

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

No annotations provided. Description mentions 'viewer mode' implying read-only but does not explicitly state non-destructiveness, required file existence, format, or error behavior. Insufficient disclosure for a file-opening operation.

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

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

Single concise sentence with clear subject-verb-object. No unnecessary words. Front-loaded with key information.

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

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

Output schema exists but description does not mention return value or behavior (e.g., what agent receives after opening). Sibling tools exist; description could be more complete given complexity of file operations.

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

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

Schema coverage is 0%, and description adds no detail about the file_path parameter (format, allowed extensions, absolute vs relative). Agent has no guidance beyond the parameter name.

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

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

Description clearly states the tool opens an existing layout file in KLayout viewer mode, using specific verb 'open' and resource 'layout file', and distinguishes from editor mode via 'viewer mode'.

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

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

No guidance on when to use this tool versus siblings like open_editor, new_layout, or layout_info. The description does not mention prerequisites or contexts.

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

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

With no annotations, the description must cover behavioral traits. It explains orientation format, array parameters (dx, dy, nx, ny), and coordinate units. However, it omits details on return value, side effects, or required state (e.g., active cell existence). The explanation is partial.

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

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

The description is very concise: two sentences plus a line for specifics. The purpose is front-loaded, and every sentence adds value. No redundant information.

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

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

Given the tool's complexity (9 parameters, array support, orientation) and lack of annotations, the description covers the main operation and key parameters. However, it does not explain output, error handling, or default behaviors. The existence of an output schema may compensate, but the description alone is incomplete.

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

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

Schema coverage is 0%, so the description must compensate. It explains orient, dx, and dy, but fails to describe x, y, nx, ny, mag, and cell in detail. The phrase 'Coordinates in um.' loosely applies to x/y but is not explicit. Overall, most parameters lack meaningful explanation.

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

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

The description clearly states the tool's function: placing an instance or array of a cell into the active cell. It mentions orientation options and coordinate units, making the purpose specific and distinct from sibling tools like create_cell or use_cell.

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

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

The description does not provide guidance on when to use this tool versus alternatives. It lacks explicit context, prerequisites, or exclusion criteria, making it weak for helping an agent decide between siblings.

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

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

The description discloses important behavioral traits: injected names (db, klayout, session), stdout capture, rebinding session possibility, and local in-process execution with full Python access. This goes beyond what annotations provide (none given), though it does not cover error handling or safety implications.

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

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

The description is concise (5 sentences), front-loaded with the core purpose, and each sentence adds distinct value (injected names, stdout capture, session rebinding, execution context). No redundant or unnecessary information.

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

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

The tool is relatively complex (script execution with injected environment), but the description omits return value details despite the presence of an output schema. It also does not address error handling or timeouts. Given the one-parameter simplicity, it is mostly complete but lacks explicit output specification.

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

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

The input schema has 0% description coverage for its single parameter 'code'. The description does not explicitly define the parameter, but context implies that 'code' is the Python script to execute. Some additional guidance (e.g., expected format, string length) would improve clarity.

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

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

The description clearly states 'Execute Python with klayout.db available (advanced)', which precisely identifies the tool's verb (execute) and resource (Python script with klayout.db). It distinguishes itself from sibling tools that are layout modification operations (e.g., add_box, add_polygon), making the purpose unambiguous.

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

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

The description implies usage for running Python scripts with special injected names, but it does not explicitly state when to use this tool versus alternatives. The term 'advanced' suggests caution, but no when-not or alternative tools are mentioned. Usage context is implied but not fully explicit.

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

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

No annotations exist, so description carries the burden. It mentions optional opening but does not disclose overwrite behavior, error handling, or path validation. Adequate but missing specifics.

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

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

Two short sentences, no wasted words, front-loaded with the key action. Highly concise.

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

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

Given only 2 parameters and an output schema, description covers main functionality. Could mention overwrite behavior or error conditions, but sufficient for a simple save operation.

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

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

With 0% schema description coverage, the description adds some meaning: path is tied to file extensions, and open_after is explained as opening in editor. However, it does not specify exact format or constraints.

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

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

The description clearly states the action 'write the current layout to a file', specifies the file extensions .gds/.oas, and indirectly distinguishes from sibling tools like 'open_layout' or 'new_layout'.

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

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

No guidance on when to use this tool versus alternatives (e.g., when to save vs. run_script), no prerequisites, and no exclusions provided.

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

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 mentions switching the active drawing cell, which implies state change, but does not disclose what happens to the previous active cell, whether permissions are needed, or any side effects. This is insufficient for a state-modifying tool.

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

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

The description is a single, clear sentence with 10 words. It is extremely concise and front-loaded with the key action and resource. No unnecessary words.

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

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

Given the tool has an output schema (per context signals), the description need not explain return values. However, with only one required parameter and a state-changing operation, more context about prerequisites (e.g., cell must exist) and the effect on the user's session would improve completeness. The description is adequate but minimal.

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

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

The schema has 0% description coverage, so the description must compensate. It adds that the 'name' parameter refers to an existing cell ('to an existing cell') and gives a concrete example ('e.g. the top cell'). While helpful, it does not specify name format, validation rules, or what constitutes a valid cell.

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

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

The description clearly states the action ('Switch') and the resource ('the active drawing cell'), and provides an example ('e.g. the top cell'). It is specific and distinct from sibling tools in its core function, though it does not explicitly differentiate from siblings like 'create_cell' or 'place_cell'.

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

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

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no conditions. It simply states the function without context about typical use cases or exclusions.

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