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

With no annotations, the description carries the full burden and does well by disclosing API mapping, default layer creation ('If omitted for "raster", a default layer is created'), and providing extensive data source context. It does not cover id conflict behavior or other side effects, so it falls short of a 5.

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 long, but well-structured with headers, tables, and code blocks that make it scannable. The opening sentence is succinct and front-loaded. The reference material is necessary for correct invocation, though it could be seen as verbose.

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 complex (7 params, nested objects) with no annotations or output schema, yet the description covers purpose, usage patterns, and available data layers comprehensively, including example invocations and selection tips. Gaps remain around duplicate ids and error handling, but overall it is sufficient for correct selection and 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?

Even though schema coverage is 100%, the description adds significant value through concrete JSON examples for source, layers, and id, plus a catalog of valid data layers with attributes and URLs. This goes far beyond the schema's simple descriptions, effectively teaching the agent how to structure 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 'Add a MapLibre source and one or more layers' and explicitly maps to `map.addSource()` and `map.addLayer()`. This specific verb+resource pairing distinguishes it from sibling tools like remove_layer and filter_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?

The description provides 'Example Usage Patterns' showing when to use add_layer for base maps and data layers, and points to filter_layer and set_layer_paint for subsequent operations. Tips like 'Always start with a base layer' imply usage context. It lacks explicit 'when not to use' statements, but the workflow is clear.

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 full behavioral disclosure. It does mention that the filter applies to 'all its sub-layers,' which is useful, but it fails to disclose whether the filter replaces an existing filter, whether the operation is reversible, or any side effects. The description is largely filled with layer catalog information rather than behavior of the tool itself.

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 first sentence is concise, but the description is dominated by a lengthy 'AVAILABLE DATA LAYERS & USAGE CONTEXT' block that is largely unrelated to the filter tool's specific operation. This boilerplate could be shortened or moved to a shared system prompt. The core tool explanation is padded with extensive examples and tips that are not all necessary for using filter_layer.

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 provides rich context about available data layers and their attributes, which is essential for constructing filters. It also gives example usage and tips. However, it omits important behavioral details (replacement semantics, reversibility) and does not describe return values or error cases. For a simple tool with no output schema, the description is functional but not completely self-sufficient.

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 100%, giving basic meaning for layer_id and filter. The description adds significant value by providing attribute names (e.g., ISO3, admin_level) and a concrete example filter expression (["==", ["get", "ISO3"], "USA"]), which helps the agent construct valid filters beyond the schema's generic description.

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 opens with 'Apply a MapLibre filter expression to a layer and all its sub-layers,' which is a specific verb+resource statement that clearly distinguishes it from sibling tools like add_layer, set_layer_paint, and remove_layer. The purpose is unmistakable and actionable.

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 includes example usage patterns and tips such as 'Filter by geography first (ISO3, admin_level) to improve performance,' which provide practical context for when to use the filter tool. It also contrasts filtering with styling through separate examples (filter_layer vs set_layer_paint), though it does not explicitly name alternatives or 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 provided, the description carries the burden. The verb 'Return' implies a read-only operation, and the output format is clarified. However, it does not disclose potential side effects, auth requirements, or behavior when the optional 'state' parameter is supplied.

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 concise sentence that conveys the core function, output format, and two primary use cases without unnecessary detail.

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 getter tool, the return format is stated, but the interplay between the optional 'state' input parameter and the returned configuration is ambiguous. With no output schema, the description should clarify whether providing a state filters or transforms the result. This gap reduces 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?

The schema covers both parameters (state and session_id) with descriptions, so baseline is 3. The description adds value by explaining that the output can be used as 'state' for other tools, which links the output format to the state parameter and clarifies the intended 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 uses the specific verb 'Return' with the resource 'current map configuration' and explicitly states the output format ('as a JSON string'). This clearly distinguishes it from sibling tools like add_layer or set_map_view, which mutate the map.

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 indicates the tool is for 'inspection or as 'state' for other tools,' which implies usage context. However, it does not explicitly state when to prefer this over list_layers or other siblings, nor does it provide exclusion criteria.

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 provided, the description carries full responsibility for behavioral disclosure. It states the core behavior (listing active layers) but does not explain how the session is identified via the optional state and session_id parameters, nor whether there are any side effects. This is a minor gap for a simple read-only operation, but without annotation support, more detail would be beneficial.

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, direct sentence with no unnecessary words, making it easily parseable and front-loaded.

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 simplicity of the tool and that the schema fully documents parameters, the description is sufficient to convey the tool's purpose. However, the lack of an output schema means the agent doesn't know what a list entry looks like, but for a simple listing tool this is acceptable. The description could mention that state and session_id are alternative ways to specify the session, but that is a minor omission.

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?

Both parameters are already documented in the input schema with full coverage, and the description adds no additional meaning. The baseline 3 applies since the schema handles the semantic load.

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 'List' and identifies the resource 'currently active layers' with session scope, clearly distinguishing from sibling tools that add, remove, set, or filter 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 provides clear context that this tool retrieves active layers in a session, but it does not explicitly mention alternatives or when not to use it. Since sibling tools like get_map_config could also return layer information, a bit more guidance would help, but the current description is adequate for a straightforward list operation.

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 a key side effect: the associated source is also removed. This adds behavioral transparency beyond a simple 'Remove layer'. However, with no annotations provided, the description still lacks details on irreversibility, error behavior, or consequences for shared sources, leaving significant gaps for a destructive 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?

The description is a single, front-loaded sentence that conveys the core action and its primary side effect with zero wasted words. It is concise and directly to the point.

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 relatively simple tool with three parameters and no output schema, the description provides the essential context: what is removed and that the source is removed as well. It is sufficient for basic invocation, though it could be improved by mentioning error conditions or reversibility, but that is covered under behavioral transparency.

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 already provides descriptions for all three parameters (100% coverage). The tool description adds no additional parameter-level meaning, so the baseline score of 3 applies.

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 specific resource ('a layer and its associated source'). It distinctively identifies this as the removal counterpart to sibling tools like add_layer and set_layer_paint, leaving no ambiguity about what the tool does.

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

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, or when not to use it. The description only states what it does, leaving the agent to infer that it should be used when a layer/source needs to be removed. There is no mention of prerequisites, fallbacks, or 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 provided, the description must disclose behavioral traits, but it only mentions applying paint 'for a layer and all its sub-layers.' It does not explain side effects, reversibility, required permissions, or behavior on invalid properties. The large layer catalog is irrelevant to the tool's behavior, so the actual behavioral coverage is minimal.

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 actual tool description is only one sentence, but the rest is a massive block of unrelated layer catalog content (base layers, vector layers, generic tips). This bloat harms conciseness and buries the relevant usage example. The front-loaded sentence is good, but the overall structure is poor for a tool description.

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 provides enough context for the core operation, especially with the styled example, but it omits details about return values, errors, or the optional state/session parameters. Given no annotations and no output schema, the description partially compensates with examples but remains incomplete for a polished agent-facing tool spec.

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 100% with basic parameter descriptions. The tool description adds value by giving concrete examples of valid property names ('fill-color', 'raster-opacity') and showing that 'value' can be a complex expression like a match on an attribute (e.g., IUCN_CAT). This goes beyond the schema's generic 'new value' description.

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 opening sentence clearly states the tool's function: 'Set MapLibre paint properties (e.g. colors, opacity) for a layer and all its sub-layers.' This specific verb-resource combination distinguishes it from sibling tools like filter_layer and add_layer, and the sub-layer scope adds precision.

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 includes a detailed example showing when to use set_layer_paint (e.g., styling by attribute with a match expression), which implies usage context. However, it lacks explicit when-to-use vs. alternative guidance, such as comparing to filter_layer or add_layer. The 'Tips' section is generic and does not address tool selection.

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 only states the core behavior without explaining session handling, the optional state parameter, or any side effects. The large block of layer information is unrelated and does not illuminate this tool's behavior.

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 purpose is front-loaded in one sentence, but the rest of the description is a massive, irrelevant block about data layers and other tools. This is not concise and most sentences do not earn their place.

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 camera-move tool, the core description is present but incomplete: it omits any mention of session_id or the state parameter and does not explain the effect on existing layers. The unrelated layer documentation detracts from 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 coverage is 100% and includes descriptions for all parameters. The description only mentions center and zoom, adding no additional semantics. Baseline 3 is appropriate.

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 first sentence clearly states 'Move the map camera to a specific center and zoom level' using a specific verb and resource. This distinguishes it from sibling tools that manage layers (add_layer, filter_layer, 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 use case is implied by the purpose statement, but there is no explicit guidance on when to use it vs alternatives like get_map_config. No exclusions are given, but the extensive layer documentation does not clarify usage context for this tool.

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