Server Quality Checklist

Tool Scores

• tomo_delete_roomC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description bears full burden. It says 'stop and remove' but gives no details on whether stopping is reversible, what side effects occur (e.g., data loss), or required permissions. For a destructive operation, more transparency is needed.

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

  Conciseness4/5

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

  The description is very concise at one sentence. It is front-loaded with the action and key precondition. Could be slightly more structured with bullet points for clarity, but no wasted words.

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

  Completeness2/5

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

  Given it's a destructive operation with 1 parameter (0% schema coverage), no output schema, and no annotations, the description is insufficient. It should disclose return behavior, error states, and effects of the operation.

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

  Parameters2/5

  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 only mentions 'room ID' generically but doesn't explain what it looks like, how to find it, or constraints. The description adds minimal meaning beyond the schema's parameter name.

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

  Purpose4/5

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

  The description uses specific verb-resource pairs ('Stop and remove a streaming room') and clarifies a precondition ('after confirming the room ID'). It distinguishes this from sibling tools like tomo_create_room or tomo_list_rooms, but could be slightly more explicit about the distinction.

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

  Usage Guidelines3/5

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

  The description implies when to use (after confirming room ID) but does not explicitly state when not to use or compare to siblings. No guidance on prerequisites like whether the room must exist or be running.

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

• tomo_get_roomA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It clearly indicates a read operation (not destructive), but it lacks detail on what happens if the room is not found, whether it returns errors, or if there are any side effects. The description adds some clarity about what is read but omits other behavioral nuances.

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

  Conciseness5/5

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

  The description is one concise sentence that front-loads the action ('read') and lists the key objects (status, peer count, connection details). There is no redundancy or fluff, making it highly efficient for its length.

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

  Completeness3/5

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

  The tool is simple with one parameter and no output schema, but the description is thin. It names the informational content but does not clarify the output structure (e.g., data types, formats, or error handling). For a read operation, this might be sufficient, but more detail on the return would improve completeness.

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

  Parameters4/5

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

  With only one parameter (roomId) and 0% schema description coverage, the description must compensate. It implies the roomId is necessary to identify the room but does not explain the format (e.g., UUID, string) or validity constraints, which could be an issue since the schema only says 'type: string'. Given the simplicity, a baseline of 4 is appropriate because the description at least ties the parameter to its purpose.

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

  Purpose4/5

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

  The description clearly states that the tool reads a room's status, peer count, and browser connection details, which conveys a specific read operation on a room resource. It distinguishes from siblings like create/control/delete but does not explicitly contrast with other read tools such as tomo_list_rooms, missing some differentiation.

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

  Usage Guidelines3/5

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

  The description implies usage for checking the status of a single room, but it does not explicitly state when to use this versus tomo_list_rooms, which might also return room statuses. There is no mention of prerequisites or context such as needing the room to exist.

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

• tomo_healthA
  3.7/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden. It only states the tool 'checks reachability' but discloses nothing about timeouts, side effects (read-only vs. state-changing), error responses, or whether it makes a network call. For a health-check tool, an agent needs to know that it is safe, non-destructive, and returns a simple success/failure – none of which is stated.

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

  Conciseness5/5

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

  A single sentence of 10 words with no fluff. Every word contributes to defining the tool's purpose. Perfectly concise for the complexity of a no-parameter health check.

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

  Completeness3/5

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

  Given the simplicity (zero params, no output schema, no annotations), the description is adequate but not complete. It does not explain what a 'reachable' response looks like or how the agent should interpret failure. A health-check tool benefits from mentioning that it returns a boolean or succeeds/fails, which is missing.

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

  Parameters4/5

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

  There are zero parameters and schema coverage is 100% (vacuous). With no inputs to describe, the description satisfies by stating the tool's action. A baseline of 4 applies because there is nothing more needed about parameters, and the description adds value beyond the schema by clarifying the tool's purpose.

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

  Purpose5/5

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

  The description uses a clear verb ('Check') and specifies the exact resource ('Tomo Streaming control plane reachability'). This cleanly distinguishes it from sibling tools that manage servers, rooms, and rooms (e.g., tomo_list_rooms lists rooms, tomo_health checks connectivity).

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

  Usage Guidelines3/5

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

  The description implies usage as a connectivity check before other operations, but does not explicitly state when to use it (e.g., 'Use before other calls to verify the control plane is up') or when not to use it. No alternatives or exclusion criteria are mentioned; agents must infer the context from sibling names.

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

• tomo_list_roomsA
  3.7/5.0
  Behavior3/5

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

  With no annotations provided, the description must carry the full burden of behavioral disclosure. It states it returns rooms and live status, which is helpful, but it does not disclose edge cases (e.g., behavior when no rooms exist, pagination limits, or authentication requirements beyond 'authenticated client'). Adequate but not rich.

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

  Conciseness5/5

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

  The description is a single, efficient sentence that conveys purpose and key detail (live status) with no wasted words. It is front-loaded and earns its place.

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

  Completeness3/5

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

  For a parameterless list tool with no output schema, the description provides basic completeness: it names the resource and indicates the return content (live status). However, it lacks details about the expected response format or any sorting/filtering behavior, which would be expected for a list operation.

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

  Parameters3/5

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

  Schema description coverage is 100% because there are zero parameters. The description correctly implies no parameters are needed ('the authenticated client's streaming rooms'). Baseline 3 is appropriate as the description adds no parametric information beyond what the schema already makes clear (no params).

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

  Purpose5/5

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

  The description uses a specific verb ('List') and resource ('the authenticated client's streaming rooms') and adds a key detail about the return value ('their live status'). This clearly distinguishes it from siblings like tomo_create_room or tomo_get_room.

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

  Usage Guidelines3/5

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

  The description implies when to use it (to list rooms for the authenticated client) but does not mention when not to use it or how it contrasts with siblings like tomo_get_room or tomo_list_stream_servers. Basic guidance is there but could be more explicit.

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

• tomo_list_stream_serversA
  3.7/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool lists available experiences, implying no modification. However, it does not mention whether listing requires authentication, how many results can be expected, or if any default filtering applies. This is minimal but does not contradict anything.

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

  Conciseness5/5

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

  The description is a single sentence with no wasted words, front-loading the key verb and resource. It is appropriately concise for a zero-parameter tool.

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

  Completeness4/5

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

  Given the low complexity (zero parameters, no output schema, no nested objects), the description is nearly complete. It states what the tool lists and the scope. A minor gap is the lack of mention about return format or behavior when no experiences exist, but overall sufficient.

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

  Parameters4/5

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

  The input schema has zero parameters and schema description coverage is 100%, so the description correctly implies no parameters are needed by stating a simple listing operation. No additional parameter details are required, and the description adds value by confirming the operation's nature.

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

  Purpose4/5

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

  The description clearly states the verb 'List' and the resource 'stream-server experiences' and specifies the scope 'on this control plane'. It distinguishes from siblings like tomo_list_rooms by naming a different resource type, though it could be more explicit about the contrast.

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

  Usage Guidelines3/5

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

  The description implies usage when you need to list stream-server experiences, but it provides no guidance on when not to use this tool or alternatives among siblings. For a simple listing tool with zero parameters, this is adequate, though explicit exclusions are missing.

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

• tomo_create_roomA
  3.9/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It states the tool creates a room but does not disclose what happens if the room already exists, if there are side effects, or what default values apply for unspecified parameters. It does not state whether this is a write or read operation, or if authentication is needed. However, the 'Create' verb in the description is consistent with a mutation, so there is no contradiction.

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

  Conciseness5/5

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

  The description is a single, concise sentence that efficiently conveys the tool's purpose with relevant examples, containing no superfluous words.

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

  Completeness3/5

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

  The description is somewhat complete for creating a room given the input schema, but it lacks details on return values (no output schema, so this is a gap) and edge cases (e.g., behavior with duplicate names). The sibling tools list suggests related tools exist, but the description does not reference them for further context.

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

  Parameters4/5

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

  Schema coverage is 100%, providing descriptions for all 3 parameters. The description adds context by listing examples of 'type' values (e.g., 'camera-stream-server'), which is not in the schema. However, it does not explain the 'source' parameter in detail, which could be ambiguous (device configuration or identifier).

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

  Purpose5/5

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

  The description clearly states the tool creates a streaming room, with specific examples of what can be streamed (camera, desktop, plugin). It uses a specific verb 'create' and resource 'streaming room', and effectively distinguishes itself from siblings like tomo_list_rooms (list) or tomo_delete_room (delete).

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

  Usage Guidelines3/5

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

  The description implies this tool is used to create a streaming room, but it does not explicitly state when to use this tool versus alternatives like tomo_control_room (presumably for controlling existing rooms) or tomo_list_stream_servers (for listing available types). There is no guidance on required prerequisites (e.g., needing a stream server type).

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

• tomo_control_roomA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It accurately states the three possible actions (pause, resume, restart), but does not disclose any side effects, prerequisites (e.g., room must be active), or whether these actions are reversible. For a control tool, this is an adequate starting point but lacks depth. Score of 3 reflects a clear but basic transparency.

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

  Conciseness5/5

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

  The description is a single sentence of 6 words—no wasted verbiage. Every word earns its place by directly stating the verb and resource. This is a model of conciseness.

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

  Completeness4/5

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

  For a simple control tool with just 2 parameters (both required, one enum), no output schema, and no nested objects, the description is nearly complete. The only minor gap is not specifying that the room must exist or be in a valid state for the action to succeed, which would improve completeness. Score of 4 is fitting given the low complexity.

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

  Parameters3/5

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

  Schema description coverage is 0%, so the description must add meaning beyond the schema. The description lists the three actions, which maps to the 'action' enum parameter. However, it does not explain the 'roomId' parameter beyond the schema or clarify any format constraints. Given only 2 parameters with 0% coverage, a baseline 3 is appropriate—the description adds some context but not enough to fully compensate.

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

  Purpose5/5

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

  The description uses a specific verb set ('Pause, resume or restart') targeting a clear resource ('a streaming room'). This makes the purpose highly distinct from siblings like 'tomo_create_room', 'tomo_delete_room', or 'tomo_get_room' which have completely different actions.

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

  Usage Guidelines4/5

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

  The description implicitly conveys when to use this tool—when you need to modify the state of a room after creation. It does not explicitly provide 'when not to use' or name alternative tools for similar tasks, but the sibling list provides enough contrast (e.g., not for creating or deleting rooms). A score of 4 is appropriate for clear but not exhaustive guidance.

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