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

No annotations are provided, so the description must carry the transparency burden. It reveals the tool is a mutation (adds layers) and details parameter behaviors, but it does not explicitly state side effects (e.g., whether it stacks layers, requires viewer initialization, or has order 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?

Well-structured with a one-line purpose followed by a clear bullet-style parameter list. While lengthy due to 13 parameters, every item adds value and is front-loaded. Some redundancy could be trimmed (e.g., repeating defaults).

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?

Parameter documentation is thorough, but missing high-level context such as when to use, prerequisites (e.g., viewer must be initialized), or expected output behavior. The output schema exists but is not referenced; description could briefly mention return type.

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 coverage, the description provides exhaustive parameter details: allowed values, defaults, and context for each parameter (e.g., layer_type enums, colormap caveat 'image only', shape_type options). This far surpasses the baseline compensation needed.

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 'Add a layer to the viewer' with a specific verb and resource. It distinguishes from sibling tools like remove_layer, set_layer_properties, and list_layers, 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?

No guidance on when to use this tool versus alternatives (e.g., init_viewer, set_layer_properties). The description only lists parameters without context on prerequisites or typical use cases.

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 supported properties (visible, opacity, colormap, etc.) and a crucial limitation: renaming via suffix is NOT supported. This helps the agent understand the tool's capability and avoids unexpected failures. Since no annotations are provided, the description carries the full burden, and it does well in revealing constraints.

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 concise opening sentence followed by a clear parameter list. It is informative without being overly verbose. A minor point is that it could be slightly more compact, but the level of detail is appropriate given the lack of schema descriptions.

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 (3 optional parameters) and the presence of an output schema, the description adequately covers the tool's purpose, parameters, and a key limitation. It does not mention what happens when no layers match or error conditions, but these may be covered by the output schema. Overall, it provides sufficient context 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 coverage is 0%, so the description fully explains each parameter: filter_type (layer type name like 'Image'), filter_pattern (glob pattern like 'seg_*'), and properties (dict with specific keys and examples). This adds significant meaning beyond the schema's minimal title fields, enabling proper usage.

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 applies property changes to multiple layers matching a filter. It specifies the action (apply), the resource (property changes), the target (multiple layers), and the selection mechanism (filter). This purpose distinguishes it from siblings like set_layer_properties, which is for individual layer 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 provides guidance on when not to use this tool: it states that renaming by appending a suffix is not supported and directs to use set_layer_properties individually for that. This implicitly tells the agent to use this tool for bulk property changes other than suffix renaming. However, it does not explicitly list all alternative tools or scenarios.

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 disclose behavior. It states that closing the viewer also clears all layers, which is useful. However, it does not mention side effects like unsaved data or whether the operation is reversible.

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 of 8 words, containing no fluff. Every word adds value, and it is front-loaded with the main action.

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 simplicity (no parameters, clear action) and the presence of an output schema (not shown but exists), the description is largely complete. It could benefit from mentioning any state dependencies, but overall it covers the essential 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?

There are zero parameters, and schema coverage is 100%. According to the rules, baseline for 0 parameters is 4. The description appropriately adds no parameter details since none exist.

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 (close) with a clear resource (viewer window) and adds the action of clearing all layers. It clearly distinguishes from sibling tools like init_viewer and configure_viewer.

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. There is no mention of prerequisites, such as requiring the viewer to be open, or comparisons 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?

No annotations provided, so description bears full burden. It explains each parameter's effect (e.g., reset_view resets camera to fit data, zoom must be >0). Does not disclose persistence or side effects, but is fairly 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?

Concise: one-line header, note on optionality, then structured list of parameters. Every sentence is useful and front-loaded with purpose.

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?

Covers all parameters well. Output schema exists, so no need for return value details. Missing context about which viewer is affected (likely active viewer), but otherwise complete.

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 fully compensates by detailing all 8 parameters with types, defaults, and meanings. Adds significant value beyond raw 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?

Description clearly states 'Configure viewer display: camera, dimensions, and grid.' It uses a specific verb-resource pair and distinguishes from siblings like init_viewer or add_layer.

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 notes that all parameters are optional and can be set in one call. Provides clear usage context but does not 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?

No annotations provided, so description fully covers behavior: namespace persistence, included objects, return value, and mode-dependent execution details (synchronous, timeout).

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?

Description is well-structured with sections, efficient sentences, and no unnecessary words. Every sentence contributes 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 moderate complexity, the description covers execution behavior, namespace, return value, and mode differences, making it fully adequate for informed use.

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 explains both parameters (code and line_limit) with default values and warnings, adding significant value beyond 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 'Execute arbitrary Python code in the server's interpreter.' and distinguishes from siblings by mentioning similarity to napari's console and persistent namespace.

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 code execution but does not explicitly state when to use this tool vs 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 full burden. It discloses that metadata is always returned, and data statistics/inline values are included when include_data or slicing is provided. It also mentions that large data returns an output_id for use with read_output. This is good behavioral disclosure, though it omits error behavior (e.g., invalid name).

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 and well-structured: a summary sentence followed by a clear parameter list. Every sentence adds value, and the format is easy to parse. It is appropriately sized for the tool.

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 complexity (4 parameters, output schema exists), the description covers input semantics well. It mentions expected output fields (shape, dtype, etc.) but does not detail the output schema structure (though output schema exists). The description is complete enough for an AI agent to use correctly.

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 description provides detailed parameter semantics: name (exact match), include_data (controls statistics and inline values), slicing (numpy-style index, implies include_data), and max_elements (threshold for inline vs stored data). This adds significant meaning 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 'Get detailed info about a layer, optionally including data.' This is a specific verb+resource that distinguishes it from siblings like list_layers (list all) and read_output (retrieve stored data). The purpose is 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 does not guide when to use this tool versus alternatives like list_layers or read_output. It explains parameters but lacks context for choosing between get_layer and sibling tools. No explicit when-to-use or when-not-to-use guidance.

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 must fully disclose behavioral traits. It clarifies that detect_only=True reports viewers without initializing, and mentions port for external bridge. However, it does not describe what 'return' means (return value) or any side effects like viewer display state.

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 front-loaded with the main purpose and includes a well-organized parameter section. However, the parameter documentation is somewhat verbose; each parameter's explanation could be more 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 5 parameters and no annotations, the description covers parameters comprehensively. However, it omits explanation of the return value despite an output schema existing, leaving a gap in 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?

Schema description coverage is 0%, but the description includes detailed parameter documentation (title, width, height, port, detect_only) explaining their purpose and defaults. This adds significant meaning beyond the bare 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 'Create or return the napari viewer, with viewer detection.' It uses specific verbs and a distinct resource, differentiating from siblings like close_viewer or configure_viewer.

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 the detect_only mode and its use case, providing context on when to use this tool without creating a viewer. However, it does not explicitly contrast with sibling tools like close_viewer or configure_viewer.

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 details parameters like upgrade and no_deps, which hint at side effects, but it does not explicitly state that the tool modifies the Python environment, requires network access, or may have other behavioral traits. With no annotations, this is adequate but not thorough.

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 front-loaded with a clear purpose statement and uses a clean parameters section. It is structured well but slightly verbose, with each parameter having a full sentence. It earns its place but could be more 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 the tool has 8 parameters and an output schema (not shown), the description covers parameter semantics well but lacks behavioral context such as prerequisites, side effects, or error scenarios. It is sufficient for basic use but incomplete for advanced understanding.

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, so the description carries the full burden. It provides detailed explanations for all 8 parameters, including examples for packages, defaults, and flag mappings (e.g., '--upgrade flag'). This adds significant meaning 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 begins with 'Install Python packages using pip,' clearly stating the action (install) and resource (Python packages via pip). This is specific and distinguishes the tool from sibling tools that deal with viewer layers, code execution, etc.

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, such as using execute_code for more flexible installation or other package managers. It only describes what the tool does.

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, and the description only states it returns a list. It does not disclose whether the operation is read-only, any side effects, authentication needs, or performance 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 extremely concise at one sentence, but it is front-loaded and to the point. However, it could be slightly more specific about 'key properties'.

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 is minimally complete, but it lacks context about the scope of layers (e.g., from current viewer).

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 tool has no parameters, and the schema description coverage is 100%. The description adds no additional parameter semantics beyond what the schema provides, which is acceptable baseline.

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 it returns a list of layers with key properties. However, it does not explicitly differentiate from sibling tools like 'get_layer' which returns a single layer, though the distinction is implicit.

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 such as 'get_layer' or 'add_layer'. The description fails to provide 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?

No annotations are provided, so the description carries the full burden. It discloses the read operation and line range, but does not mention idempotency, caching, or any side effects. The basic behavior is clear, but no additional traits are described.

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 with a single-sentence purpose followed by a clear parameter list. It is well-structured and front-loaded, though the parameter descriptions could be slightly more compact.

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 existence of an output schema (not shown), the description adequately covers reading output with line range. It is complete for a read-only tool with three parameters, though it does not describe the return format.

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 explains each parameter's meaning and default values (output_id as unique ID, start as 0-indexed line number, end as exclusive with -1 for end). This adds value beyond the schema's minimal titles and types.

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 'Read stored tool output with optional line range,' which is a specific verb and resource. It distinguishes from sibling tools that deal with layers and viewers.

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 is provided. The description lacks context for appropriate usage scenarios.

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 should fully disclose behavioral traits. It only states 'Remove a layer by name' without indicating if the removal is permanent, reversible, or has side effects on other layers. For a destructive operation, this is insufficient transparency.

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 extremely concise with a single sentence, which is front-loaded. However, it is too minimalist for a tool with no additional details; conciseness here sacrifices usefulness.

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?

While an output schema exists (not shown), the description does not mention return values or the outcome of removal. Given the lack of annotations and parameter details, the description is incomplete for an agent to fully understand the tool's behavior.

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 no meaning beyond the input schema for the single parameter 'name'. Schema coverage is 0%, meaning the description must compensate, but it merely repeats parameter existence. No format or constraints are described.

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 'Remove' and the resource 'layer by name'. It is specific and directly conveys the tool's function, distinguishing it from sibling tools like list_layers or set_layer_properties, though no explicit differentiation is provided.

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?

There is no guidance on when to use this tool versus alternatives like add_layer or apply_to_layers. The description lacks context on prerequisites, effects, or best practices, leaving the agent without clear decision-making support.

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 must carry the burden. It does not disclose any behavioral traits such as side effects, reversibility, or triggers, only the mechanics of the parameters.

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 short and front-loaded. It could be slightly more concise by merging the initial line with the parameter instructions, but it is efficient overall.

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 has an output schema but the description does not mention the return format. It explains the parameter mutex well, but lacks context on what happens after reordering (e.g., confirmation, new order).

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%, but the description adds meaning by explaining that name identifies the layer and index, before, and after are mutually exclusive with specific semantics (absolute index vs. relative to layer 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?

The description clearly states 'Reorder a layer by name,' specifying the verb and resource. It is distinct from sibling tools like add_layer, remove_layer, and list_layers.

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 gives explicit instructions on using exactly one of index, before, or after. However, it does not provide guidance on when to use this tool versus alternatives like set_layer_properties.

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 full responsibility. It describes the basic save operation but does not disclose if files are overwritten, required permissions, or error behavior. This is a significant gap.

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 purpose sentence and parameter list, making it readable. It is slightly verbose with redundant formatting but still efficient.

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 the key functionality and parameter details. However, it lacks information on file overwrite behavior and error handling. Given that an output schema exists, return values are not needed, but behavioral completeness is only moderate.

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 compensates well by explaining each parameter: name, path (with extension inference and supported formats), and format (optional override). Adds meaningful context 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 it saves a layer's data to a file, with a specific verb and resource. It distinguishes from sibling tools like add_layer or remove_layer, implying saving to persistent storage.

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 the parameters and how format is inferred, but does not explicitly state when to use this tool over siblings or any prerequisites. It provides context for parameter 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 provided, so description must disclose behavior. It explains the two modes, saving options, and interpolation limiting file size. However, it does not mention error handling, auth needs, or return format details (though output schema exists). The description is adequate but missing some behavioral context.

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 and well-structured: a brief overall purpose, then a parameter list with detailed explanations. It front-loads the main functionality and each sentence adds value. No unnecessary fluff.

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 6 parameters, no annotations, and an output schema exists, the description covers the core functionality and parameter usage. It explains both modes and key options. However, it omits some edge cases (e.g., error if axis without slice_range) and does not reference the output schema for return values. Overall, fairly complete for an agent to use correctly.

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 does a good job explaining all 6 parameters: canvas_only, save_path, axis, slice_range, interpolate_to_fit, save_dir. It provides clear semantics, including slice string examples and interpolation purpose. However, it does not explain the anyOf types (e.g., string alternatives for boolean) and misses details on default return when no save_path given.

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 purpose: taking a screenshot or timelapse series. It distinguishes between two modes (single vs timelapse) with specific parameter guidance. The verb 'take' and resource 'screenshot' are precise, and no sibling tool has similar functionality.

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 explicit usage guidance: when to use single screenshot (no axis/slice_range) vs timelapse (provide both). It explains parameters like canvas_only, save_path, and interpolation. However, it lacks explicit 'when not to use' or comparison to alternatives, though no similar siblings exist.

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, and the description only says 'comprehensive information' without detailing what data is returned (e.g., viewer state, layer list, settings). The tool's read-only and non-destructive nature is implied but not explicitly stated.

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, no unnecessary words. Front-loaded with the key action and target.

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?

Tool is simple with no parameters and an output schema exists to explain return values. However, the description is vague ('comprehensive information') and could be more specific about what session data is included, especially given the variety of sibling 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?

Tool has no parameters; the input schema is empty. Since schema coverage is 100% (no parameters to describe), baseline is 4. Description does not need to add parameter details.

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 'Get comprehensive information about the current napari session', specifying a distinct verb and resource. This differentiates from sibling tools focused on layers, viewers, or code execution.

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 like get_layer or list_layers. The description does not provide context for appropriate invocation.

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 must carry the full burden. It notes that setting active=False has no effect, but it does not disclose prerequisites (e.g., layer existence), side effects, or error behavior. This is insufficient for a mutation 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 concise, front-loaded with the main purpose, and well-structured with a 'Parameters' section. Every sentence adds value with no repetition or fluff.

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, mutation), the description covers parameter semantics but omits return value description (though output schema exists), error handling, and preconditions like layer existence. It is adequate but has clear gaps.

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 compensates by explaining each parameter's purpose (e.g., 'Layer name (exact match)', 'Standard layer rendering properties', 'Rename the layer'). However, the explanation for rendering properties is vague, and exact accepted values (e.g., colormap names) are not given.

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 'Set properties on a layer by name,' identifying the verb (set) and resource (layer properties). It distinguishes from sibling tools like add_layer, get_layer, and remove_layer by focusing on modifying existing layers.

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 modifying layer properties but does not explicitly state when to use this tool versus alternatives. No exclusions or alternative tool names are provided.

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