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

With no annotations, the description must bear the burden. It discloses key behavior (raises if absent), which is essential for a mutation-like assertion. However, it doesn't mention return value or side effects, though for an assertion tool this may be sufficient.

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, clear and front-loaded. No wasted 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?

For a simple 1-param assertion tool with output schema present (though not shown), the description is largely complete. It covers the core behavior, though it could mention the return type or success 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?

Schema coverage is 0% (no descriptions in schema). The description adds meaning by stating 'element containing text', but lacks details like case sensitivity, exact match vs substring, or whitespace handling. Partially compensates but not fully.

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 (assert), resource (element containing text on screen), and behavior (raises if absent). It distinguishes from sibling tools like tap_text and wait_for_text by focusing solely on presence check.

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?

Description implies the tool is for checking presence, but lacks explicit guidance on when to use vs alternatives like wait_for_text. No when-not or prerequisites mentioned.

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. The description discloses the basic behavior (launching an app) but does not detail side effects, error conditions, or permission 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?

A single sentence that front-loads the purpose and provides an example. No wasted 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?

For a simple tool with one parameter and no annotations, the description is sufficient for an agent to understand the core function. However, it does not describe the output or error states.

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 adds value by explaining that 'package' is an Android package name and providing an example. This compensates for the lack of schema 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 clearly states the action ('Launch an app') and the resource ('by its Android package name'), with a concrete example. It distinguishes from sibling tools like 'stop_app' which are about 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?

No explicit guidance on when to use or when not to use this tool. The usage is implied but no alternatives or exclusions are mentioned.

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

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

No annotations are provided, so the description must cover behavioral traits. It does not mention whether the tool is read-only, requires permissions, or any performance implications. As a listing operation, it's likely safe, but the lack of explicit disclosure reduces 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 a single sentence with no superfluous words. It is front-loaded with the verb and resource, directly conveying the tool's 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?

Given the tool has zero parameters and an output schema exists, the description is complete. It specifies the output includes device state with enumerated possibilities, leaving no ambiguity for the agent.

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 no parameters, so the description cannot add meaning beyond the schema. However, the description implicitly covers the tool's scope (all connected devices) which is sufficient. Baseline 4 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 description clearly states the action (List), the resource (connected Android devices), and the information provided (state with specific enum values: device/unauthorized/offline). It effectively distinguishes the tool from sibling interaction tools like tap or screenshot.

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 when to use the tool (when needing to know connected devices and their states), but provides no explicit guidance on when not to use it or alternatives. For a simple listing tool, this is adequate but not exceptional.

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 bears full burden. It states the action (press) but does not disclose side effects, return behavior, or what happens on invalid input. The behavior is straightforward 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 a single, concise sentence that front-loads the action and lists examples. No unnecessary words or redundancy.

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 tool with one parameter and an output schema (exists but not shown), the description provides adequate context. It could mention expected output briefly, but the action is clear enough 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?

The one parameter 'key' has no schema description (0% coverage). The description compensates by listing valid values (back, home, etc.) and mentioning raw KEYCODE_*, adding crucial meaning beyond the empty 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's purpose: press a key. It lists specific keys (back, home, etc.) and includes raw KEYCODE_*, distinguishing it from sibling tools like tap or swipe that touch the screen.

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 by listing keys but does not explicitly guide when to use this tool versus siblings like tap or type_text. It lacks context on alternatives or prerequisites.

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 carries full burden. It states it's a compact text list and cheaper than screenshot, which are important behavioral traits. Could mention if it's a live snapshot or requires permissions, but sufficient for a simple read 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?

Two concise sentences, front-loaded with purpose and key benefit. Every word adds value, no 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 no parameters and an output schema (not detailed), description is fairly complete: it states what it returns and its use. Could add more about output format or integration with sibling tools, but is adequate.

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 has zero parameters, baseline score is 4. Description adds no parameter info, but none 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?

Description clearly states it returns a compact text list of on-screen elements with label, tap point, and id. Distinguishes itself from screenshot by noting it's cheaper and used to choose what to tap.

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 says 'use this to choose what to tap', guiding the agent to use it before tapping. Contrasts with screenshot but does not explicitly mention alternatives like assert_text or tap_text, though context 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 carries full burden. It indicates a non-destructive read operation (capturing a screenshot) without modifying device state. However, it could explicitly state that it is read-only or mention any potential side effects like requiring permissions.

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. It is front-loaded with the action and format, making it efficient for an AI agent to parse.

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 there are no parameters, no required fields, and no output schema, the description adequately covers what the tool does and why. The agent can correctly infer how to invoke it (no arguments needed) and what to expect.

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 no parameters in the input schema, so the description adds value by specifying the output format (PNG) and the use case. With 0 parameters, baseline is 4, and the description meets that.

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 'capture', the resource 'current screen', the format 'PNG', and the purpose 'so you can visually inspect it'. It distinguishes itself from sibling tools like tap or type_text, which perform different actions.

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 when visual inspection of the screen is needed, but does not explicitly state when to use this tool versus alternatives like screen_size or assert_text. No exclusions or when-not guidance is 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 full burden. It states the return format but does not disclose any potential side effects, error conditions, or that the tool is read-only. The behavior is minimal enough to be inferred, but transparency is lacking.

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 front-loads the key information. Every word is necessary, with no waste.

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 a simple output (with an existing output schema), the description is complete enough. It explains the return format explicitly.

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 does not need to add parameter information. Baseline 4 is appropriate for no 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 returns the device screen size in a specific format 'WIDTHxHEIGHT', which is a specific verb+resource. It distinguishes from siblings like screenshot or screen which have different purposes.

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 explicit guidance on when to use this tool versus alternatives. Usage is implied as a simple getter, but no context on prerequisites or exclusions is 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?

No annotations provided, so the description bears full responsibility. It labels the action as 'force-stop' but does not disclose system effects, permissions required, or side effects on app data.

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 short (one phrase) with no wasted words. While it could be more structured, it is efficient for a single-parameter 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?

Despite having an output schema (not shown), the description does not explain return values or prerequisites. For a destructive action like force-stopping an app, the description lacks necessary contextual 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?

With 0% schema description coverage, the parameter 'package' is only described as 'by package name'. No format or example is given, though the hint is minimally helpful.

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 'force-stop' and resource 'app' with the method 'by package name'. It clearly states the tool's function and distinguishes it from siblings like 'launch_app'.

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, nor any prerequisites or exclusions. The description only states what it does, not when it is appropriate.

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 bears full responsibility. It does not disclose swipe duration, distance, whether it triggers events like scrolling, or any effects. The start point is specified but other behavioral traits are missing.

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 information. Every word is necessary and directly conveys the tool's function.

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 the presence of an output schema (which presumably documents return values), the description is minimally adequate. However, it lacks any mention of use cases, relationships to other tools, or constraints like supported screen contexts.

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 parameter 'direction' has 0% schema description coverage, but the tool description lists the valid values (up, down, left, right), which the schema does not provide as enums. This adds essential meaning beyond the bare property 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 explicitly states the action (swipe) and the possible directions (up, down, left, right) with a specific starting point (center of the screen). This clearly distinguishes it from sibling tools like tap or type_text, which involve different gestures.

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, such as tap or scroll gestures. The description does not specify scenarios (e.g., scrolling menus, dismissing cards) or exclude irrelevant 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 should disclose behavioral traits. It fails to mention whether tap is a single click, long press, or other action, nor any prerequisites or side 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, concise sentence. However, its brevity sacrifices necessary detail, so it scores average for conciseness.

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 simple but the description is incomplete: it does not cover coordinate system, behavior type, or any edge cases. An output schema exists but does not compensate for missing parameter semantics.

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%, yet the description adds no meaning to parameters x and y beyond 'absolute screen coordinates'. No details on units, range, or coordinate origin are provided.

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 'Tap at absolute screen coordinates' clearly states the action (tap) and the target (screen coordinates), distinguishing it from sibling tools like swipe or tap_text.

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 tap versus alternatives like tap_text, swipe, or wait_for_text. The description lacks context for decision-making.

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 discloses that tapping is on the first match and supports exact matching, but does not mention error handling, waiting behavior, or what happens if no element is found.

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 information. Every word serves a 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?

For a simple tap-by-text tool, the description covers the core functionality and parameters. It is mostly complete, though it could mention waiting or scrolling behavior. An output schema exists, so return values don't need description.

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 both parameters: 'text' is for substring matching, and 'exact' changes to exact match. This adds valuable meaning beyond the schema, which only provides names 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 the action (tap) and the target (first element whose text/description contains the given text). It distinguishes from sibling tools like 'tap' (which taps at coordinates) and 'type_text' (which types).

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 tapping based on text content but does not explicitly state when to use this tool over alternatives like 'tap' or 'assert_text'. No when-not or alternative naming is 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 exist, so the description carries the full burden. It discloses operation on 'currently focused field' but does not specify behavior when no field is focused, text overflow, or special character handling. Adequate but 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?

Single sentence, front-loaded with key action and target. No waste.

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 simple tool and existence of an output schema, the description is minimally complete. It mentions the critical precondition ('focused field') but omits prerequisites, error conditions, or how the text is entered (e.g., character by character). Some gaps remain.

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%. The description does not add meaning beyond the schema: it only implies the parameter is the text to type. No details on format, encoding, 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?

Description clearly states the action ('Type text') and the target ('the currently focused field'). It distinguishes from sibling tools like 'tap_text' (tap on text) and 'press_key' (press a key).

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 'assert_text' or 'tap_text'. The description does not explain prerequisites or when not to use it.

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 waiting up to timeout seconds, but fails to state behavior on timeout (error or return value) or polling frequency. With no annotations, this gap is significant for a blocking 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 10-word sentence with main action front-loaded and timeout appended in parentheses. Every word is necessary; excellent conciseness.

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 and presence of output schema, the description is incomplete: no return value, no timeout error behavior, no polling details. Insufficient for a core waiting tool among 12 siblings.

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 has 0% description coverage; description mentions 'text' and 'timeout' but does not clarify text matching (exact/partial) or timeout units/format. Adds minimal meaning beyond field names.

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 that the tool waits for an element containing text, with a verb-resource structure. It distinguishes from siblings like assert_text (assertion) and tap_text (interaction), but lacks explicit timeout failure behavior.

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 versus alternatives (e.g., assert_text) or on prerequisites. The description implies usage for waiting before interaction, but does not specify conditions or exclusions.

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