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

With no annotations provided, the description carries the full burden of behavioral disclosure. It correctly indicates this is an additive mutation, but it does not mention any limits on player count, whether the test must be actively running versus simply started, or what happens if the test is not running. This is thin coverage for a mutating 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?

One sentence with no filler. The core verb, object, and required context are all front-loaded, making it immediately scannable.

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 one-parameter tool, the description is nearly sufficient, but it leaves the meaning of the 'players' parameter unexplained and provides no behavioral guardrails. Given the absence of annotations and output schema, a bit more detail about expected usage and constraints would make it fully 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?

The schema description coverage is 0%, so the description must compensate for the undocumented 'players' parameter. The tool name and description imply that 'players' is the count of simulated clients, but the description never explicitly states that the number parameter controls how many clients are added.

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

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

The description uses a specific verb ('Add') with a clear resource ('simulated clients') and a context ('running multiplayer test'), which clearly separates it from siblings like start_test and stop_test. An agent can understand the tool's function without opening the schema.

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 phrase 'running multiplayer test' implies the tool should be used after start_test, but it does not explicitly say when to use it versus alternatives or mention any exclusions. Usage context is present but implied rather than stated.

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 burden. It discloses that the tool reads (non-destructive) and that logs are 'captured from connected sessions,' implying a session must be connected. It also hints at pagination behavior via `since`. However, it does not mention any side effects, rate limits, or data volume considerations.

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

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

The description is two sentences with no filler. The first sentence front-loads the purpose, and the second adds a concrete usage tip. Every word contributes.

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

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

For a tool with 5 parameters, no output schema, and no annotations, this description is too sparse. It does not explain the return format, the meaning of the filter parameters, or any prerequisites beyond connected sessions. An agent would need to infer or experiment to use it 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?

Schema description coverage is 0%, so the description must explain parameters. It only explains `since` ('use with the last seq to page'). The remaining parameters (level, limit, target, contains) are left entirely undocumented, leaving an agent to guess their types and purposes.

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 states a specific verb and resource: 'Read Studio Output (LogService) captured from connected sessions.' This clearly identifies the tool's function as retrieving logs. It does not explicitly differentiate from sibling tools, but the resource is distinct enough.

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 a specific pagination instruction: 'Use `since` with the last seq to page.' This gives practical guidance for one parameter. However, it does not state when to use this tool versus alternatives like studio_status or get_tree, nor any 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?

No annotations are provided, so the description carries the full burden. It does not disclose whether the tool is read-only, how depth behaves, what happens for invalid paths, or whether it returns a tree structure. The description only states what it describes, not how it behaves.

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 and front-loads the core purpose with a concrete example. It is concise, though it could be more structured by adding parameter details.

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

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

For a tool with 3 parameters, no annotations, and no output schema, the description is too thin. It does not explain the meaning of 'depth' or 'target', nor what the returned hierarchy looks like. An agent would likely need to guess or inspect other tools to use it 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?

Schema description coverage is 0%, and the description only explains the 'path' parameter via an example. 'depth' and 'target' are not explained at all; 'target' is a $ref to 'path', which is confusing and not clarified. The description does not compensate for the schema's lack of documentation.

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 states a specific verb ('Describe') and resource ('instance hierarchy under a path'), and gives a concrete example ('Workspace.Camp'). It is clear what the tool does, though it does not explicitly distinguish it from siblings like list_gui.

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 given on when to use this tool versus alternatives such as list_gui or get_logs. The example path format is helpful, but there is no context about typical use cases or exclusions.

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

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 operation is a listing and names the output fields, but it does not state whether the tool is read-only, whether a live play-test is required, or how it behaves if target is omitted.

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 filler. It communicates the operation, resource, and key output attributes efficiently.

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

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

With no annotations and no output schema, the description needs to cover return format and parameter semantics, but it only partially describes output fields and leaves 'target' undefined. The agent cannot fully determine how to invoke the tool 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 schema has 0% description coverage for the 'target' parameter, and the description does not explain what target means or what values it accepts. The phrase 'play-test client' offers a minimal hint, but the agent is left guessing the target's format and optionality.

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 a clear resource ('PlayerGui hierarchy of a play-test client'), and even names the data returned (positions, visibility, text). This is specific enough to distinguish it from generic siblings like get_tree 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 phrase 'play-test client' implies this tool is used during a play-test session, but the description does not explicitly state when to use it versus alternatives or what prerequisites are required. The usage context is inferable, not stated.

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 carry full behavioral burden. It discloses that reloading occurs in every connected session, but it does not mention side effects (e.g., state loss, script re-execution, or whether existing sessions will be disrupted). For a reload operation without annotation coverage, 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?

A single concise sentence that front-loads the action, target, and scope. No filler words; every element earns its 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?

The description is technically sufficient for a parameterless tool but lacks usage context and behavioral side effects. With no annotations and no output schema, an agent would still be uncertain about when to invoke it and what happens to sessions. Adequate but with 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?

The tool has zero parameters, so the description adds no parameter-level meaning. Baseline 4 applies because no parameter documentation is 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 a specific action (hot-reload), a specific resource (plugin/Core.luau), and a scope (every connected session). This distinguishes it from siblings like run_luau (arbitrary code execution) and sync_project (project syncing).

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 when-to-use or alternative guidance is provided. The hot-reload wording implies usage after editing Core.luau, but the description does not state when to prefer this over run_luau or other siblings, leaving usage to the agent's inference.

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 key behavioral traits: code may yield (task.wait), `plugin` is available in scope, and the tool returns print/warn output plus returned values. It also reveals that the target can be a session id, which implies stateful execution. With no annotations provided, the description carries the full burden, and it does a good job of setting expectations about execution context and output. It doesn't mention side effects or persistence, but for a code execution tool, the disclosed traits are substantial.

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 compact and front-loaded: it states the action, the environment, the output, and the key execution caveat in the first sentence. The second sentence lists targets efficiently. Every sentence earns its place, and there is no filler or repetition of schema fields.

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 code execution tool with no output schema and no annotations, the description covers the essential context: what it runs, where it runs, what it returns, and the available targets. It could mention timeout behavior or error handling, but the `timeoutSec` parameter name implies a timeout. The sibling tools are all distinct enough that an agent can select this tool correctly. A 4 is appropriate because it's nearly complete but leaves minor gaps around failure modes and exact 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?

Schema description coverage is 0%, so the description must compensate. It explains the `code` parameter implicitly (the code to execute) and the `target` parameter explicitly by listing valid values (edit, server, client, client:<PlayerName|n>, session id). It does not explain `timeoutSec`, but the name is self-explanatory. The description adds meaning beyond the bare schema, especially for `target`, which would otherwise be ambiguous.

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 executes Luau code in a Studio DataModel and returns print/warn output plus returned values. It also specifies the available execution targets (edit, server, client, client:<PlayerName|n>, session id), which distinguishes it from sibling tools like get_logs or screenshot. The verb 'Execute' plus the resource 'Luau in a Studio DataModel' makes the purpose unambiguous.

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

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

The description provides clear context on when to use this tool: when you need to run Luau code and capture output. It lists the target options, which helps the agent choose the right execution context. However, it doesn't explicitly state when NOT to use it or name alternative tools (e.g., use get_logs for reading logs, use start_test for running tests). The target list partially compensates by implying the tool is for arbitrary code execution rather than specific test or log operations.

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 behavioral burden. It discloses macOS window focusing, the no-screen-access nature of render mode, and camera movement before capture. It does not mention output format, permissions, or error behavior, but the disclosed traits are significant.

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?

Four sentences pack a lot of mode, parameter, and platform detail without wasted words. The information is front-loaded and scannable, though a bulleted structure could improve readability.

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

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

For a tool with no annotations, no output schema, and 8 parameters, the description covers the core modes and key parameters but omits the meaning of four parameters and the return format. This is a meaningful gap for an agent deciding how to invoke it.

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

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

Schema coverage is 0%, and the description explains mode, title, target, and the camera object's shape (position, lookAt, fov, release). However, width, method, exposure, and includeUi are left completely unexplained, so agents must guess at their meaning.

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 'See what Studio shows' and then details two capture modes—window and render—with distinct behaviors. This clearly identifies the tool's purpose as capturing Studio visuals and differentiates it from sibling tools like get_logs or studio_status, which are unrelated.

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

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

The description explains when to use window mode by default, when to pass title, and when render mode is preferable ('works without screen access'). It does not explicitly state when not to use the tool or name alternatives, so it falls just short of a 5.

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

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

With no annotations, the description must carry the behavioral load. It does disclose one key behavior: 'Waits until the server and client sessions connect.' However, it does not mention whether the call blocks beyond connection, what side effects occur, or what the return/value signals are.

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 compact and front-loaded: it states the core action first, then summarizes modes, then notes the connection wait. Every sentence adds useful information without 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?

The description is sufficient for common default usage and explains mode behavior, but it lacks an explanation of waitSec and gives no output/return context. With no annotations and no output schema, this is a notable gap, though the tool is still usable for simple calls.

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 is the only source of parameter meaning. It explains mode values and the players range ('players 1-8 simulated clients'), but waitSec is completely unexplained, leaving a semantic gap for one of the three 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 opens with a concrete verb and resource ('Start a Studio test from the edit DataModel') and lists the supported modes. This clearly distinguishes it from siblings like stop_test and makes the tool's purpose immediately obvious.

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

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

The description provides clear context for when to use the tool: when starting a Studio test. It also covers mode-specific guidance and defaults, though it does not explicitly name alternatives or state when not to use this tool.

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 burden. It discloses a mutation ('End') but doesn't mention side effects, such as whether the session state is saved, whether it fails if no session is running, or whether it is idempotent. Minimal disclosure beyond the basic action.

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

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

A single, front-loaded sentence with no filler. Every word earns its place, and the action is stated immediately.

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 stop action with no params or output schema, the description is nearly complete. It could mention behavior when no session is running, but that's a minor gap given the tool's simplicity.

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 zero parameters, so the schema provides complete coverage. The description correctly adds no parameter detail, meeting the baseline of 4 for no-parameter tools.

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 states a clear, specific verb ('End') and resource ('running Studio test session'). It unambiguously distinguishes from the sibling 'start_test' by its opposite action, and no other sibling does this.

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 given on when to use this tool vs alternatives. While the opposite 'start_test' implies it should be used after starting, the description never states prerequisites, conditions, or when not to call 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?

With no annotations, the description carries the burden of behavioral disclosure. It does disclose the scope of the listing (edit DataModel, play-test server, clients), which adds value beyond the schema (which is empty). However, it doesn't mention potential side effects, permissions, or session states (e.g., if no session is connected), so it's minimal but not misleading.

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 ('List connected Roblox Studio sessions') and then specifies the exact session types. No wasted words; every phrase earns its 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 status-listing tool with no parameters, the description is complete: it tells the agent what it does and what it returns. With no output schema, the description does not detail the return format (e.g., list of session IDs), but for a status tool, the core purpose is clear enough for an agent to invoke it correctly.

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

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

The tool has zero parameters, and the schema is empty with 100% coverage (vacuously). Per the rubric, baseline is 4 for zero-parameter tools dropped to baseline 3 due to high coverage. The description adds no parameter semantics needed; it's clear the tool takes no input. Thus 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 tool's function: listing connected Roblox Studio sessions, and specifies the types of sessions (edit DataModel, play-test server, play-test client). This is a specific verb+resource combination that distinguishes it from sibling tools like run_luau or get_logs.

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 as a status/discovery tool, but it does not explicitly state when to use it versus alternatives. Given the sibling tools include run_luau and start_test, the description could have mentioned that this is useful before running scripts or tests, but it doesn't. It's adequate but not explicit.

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

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

With no annotations, the description carries the full behavioral burden and handles it well by disclosing that the tool creates/updates scripts and folders and removes previously synced instances that no longer exist on disk. This warns the agent about destructive side effects. It does not cover failure modes or conflict handling, but the core mutation behavior is 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?

Two sentences: the first front-loads the action and mode; the second lists effects. There is no filler or repetition.

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 single-parameter tool with no annotations or output schema, the description gives enough context to call it safely: what to pass, where it acts, and what side effects to expect. It does not describe return values or error outcomes, but those are less critical for invoking a sync operation.

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

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

While the schema only says 'project' is a required string with no description, the tool description explains that it represents a Rojo project file, which is the key semantic needed to invoke it correctly. It stops short of spelling out path/form requirements, so it is not perfect.

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?

States a specific action ('Push scripts from a Rojo project file') and the target context ('open place, edit mode only'), then details the side effects of the sync. The combination of Rojo sync with create/update/remove behavior sets it apart from sibling tools like run_luau or reload_plugin.

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 makes the intended use clear: synchronize a Rojo project into the currently open place, and explicitly restricts use to edit mode. It does not name alternative sibling tools or provide when-not-to-use guidance beyond the edit-mode constraint.

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