Server Quality Checklist

Tool Scores

• nst_get_browsersB
  3.1/5.0
  Behavior2/5

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

  With no annotations, the description must carry behavioral disclosure. 'List' implies a read operation, but the description doesn't disclose that status filtering can return non-running instances, nor does it describe output format 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.

  Conciseness5/5

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

  A single sentence that is direct and free of unnecessary detail.

  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 minimal and lacks return value details or relationship to sibling tools. For a simple list tool it is usable, but the running/status inconsistency leaves a gap.

  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?

  The only parameter 'status' is fully described in the schema with enum values. The description adds no extra parameter meaning beyond the phrase 'running', which might be misinterpreted as a fixed state rather than the default filter.

  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?

  Lists NSTBrowser instances, a distinct resource compared to sessions/profiles. The verb 'List' and resource are clear, but the qualifier 'running' is slightly misleading since the status filter supports starting/stopping as well.

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

  Usage Guidelines2/5

  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 list_sessions or nst_get_profiles. 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.

• switch_sessionB
  3.1/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It only states the basic action without revealing whether the session ID must exist, whether the previous session is deactivated or remains available, or any side effects. This is insufficient for a state-changing tool.

  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, 'Switch the active browser session', with no filler or redundant information. It is immediately understandable and efficiently conveys the core purpose.

  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 simple one-parameter tool, the description is minimally adequate, but it lacks important context about prerequisites (e.g., session must exist) and consequences (e.g., affects subsequent calls). With no annotations or output schema, more context would be beneficial.

  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?

  The input schema already provides a clear description for sessionId: 'Session ID to switch to', and schema coverage is 100%. The tool description adds no additional parameter-level detail, but since the schema covers it fully, this is acceptable.

  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 'Switch the active browser session' clearly identifies the action (switch) and the target resource (active browser session). It distinguishes implicitly from siblings like create_session and close_session by focusing on changing state rather than creating or destroying, though it could be more explicit about its unique role.

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

  Usage Guidelines2/5

  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. The description does not mention prerequisites such as listing sessions first, nor does it explain that switching affects subsequent operations. There are no explicit when-to-use or when-not-to-use instructions.

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

• nst_get_profilesB
  3.2/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of disclosing behavior. It does not mention that this is a read-only operation, any required permissions, or whether the list is static or dynamic. It also fails to describe any side effects or limitations, leaving the agent to infer safety from the name alone.

  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 is front-loaded and free of fluff. It communicates the core purpose efficiently without wasting words, achieving excellent conciseness for a simple listing tool.

  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?

  The tool has four parameters for filtering and pagination, but the description does not mention these capabilities, nor does it describe what the return value looks like in the absence of an output schema. The description is too minimal to fully inform an agent about how to effectively use the tool in a real scenario.

  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?

  The input schema has full coverage for all 4 parameters, so the baseline is 3. The description adds no extra meaning beyond what the schema already provides, such as indicating that 'page' and 'pageSize' control pagination or that 's' filters results. The description is neutral and does not mislead, hence a 3.

  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 'List available NSTBrowser profiles' clearly states the action (List) and the resource (NSTBrowser profiles). It distinguishes from siblings like 'create_session' and 'nst_get_browsers' by targeting profiles specifically, making its purpose unambiguous.

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

  Usage Guidelines2/5

  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 whether to use it before selecting a profile or how it relates to session management. The description gives no context for choosing this tool over siblings like 'nst_get_browsers' or 'list_sessions'.

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

• list_sessionsA
  3.5/5.0
  Behavior2/5

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

  There are no annotations, so the description carries the full burden of behavioral disclosure. The word 'active' adds a slight qualification, but the description does not explain what constitutes an 'active' session, the shape of the returned data, or whether it is a safe read-only operation. This is minimal and leaves significant behavioral questions unanswered.

  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 front-loads the core action and object. Every word is essential and there is no filler, making it highly efficient.

  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 tool's simplicity (0 params, no output schema), the description is minimally adequate but leaves out important details such as what fields are returned for each session and what happens if no sessions are active. For a complete picture, the tool would benefit from specifying return structure or edge cases, so it is not fully complete.

  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 tool takes zero parameters, and the empty input schema fully defines this. Per the rubric, 0 params earns a baseline of 4. The description adds no parameter information, but none is needed since there are no arguments to explain.

  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 clearly identifies the resource as 'active browser sessions'. It is unambiguous and distinguishable from sibling tools like create_session, switch_session, and close_session by focusing on listing rather than state changes.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives like nst_get_profiles or nst_get_browsers. While the purpose is clear, the absence of any contextual usage hints means a user might wonder whether to list sessions or browsers.

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

• close_sessionA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It discloses the core action ('close') and the effect ('disconnect from NSTBrowser'), but it does not detail side effects, irreversibility, potential errors, or whether the operation is idempotent. This is acceptable for a simple close/teardown operation but leaves some behavioral aspects implicit.

  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, well-structured sentence that fully covers the tool's purpose without unnecessary words. It earns its place and is immediately understandable.

  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 low-complexity tool with one parameter and no output schema, the description provides sufficient information: it states what is closed and what disconnect occurs. Its sibling context clarifies when it would be used. Minor gap: it does not mention return values or error cases, but these are less critical for a close 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 coverage is 100% with the 'sessionId' parameter already described as 'Session ID to close'. The description adds no additional meaning or context beyond the schema, so it does not improve on the baseline. It correctly maps to the single parameter but provides no extra semantic value.

  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 ('Close') and clearly identifies the resource ('a browser session') plus the additional effect ('disconnect from NSTBrowser'). This distinguishes it from sibling tools like create_session, list_sessions, and switch_session, making its purpose unambiguous.

  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 usage context is implied by the verb and resource, but the description does not explicitly state when to use this tool versus alternatives, nor does it mention any preconditions (e.g., session must exist) or exclusion cases. It is adequate but lacks explicit guidance.

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

• create_sessionA
  4.1/5.0
  Behavior4/5

  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 explains the two modes (existing vs. temporary profile), the CDP connection mechanism, and that all parameters are optional with sensible defaults. It does not mention potential side effects like persistence or cleanup, but for a creation tool this is acceptable.

  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 two sentences with no filler. It front-loads the core purpose and then explains the key usage modes, making it highly efficient and easy to scan.

  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 has 7 parameters and no output schema, but the description only explains the primary functionality. It does not mention return values (e.g., session ID) or how the created session relates to sibling tools like switch_session or close_session. This leaves a gap for an agent that needs to know what to expect after invocation.

  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%, so the description adds marginal value beyond the schema. It clarifies that profileId is for connecting to an existing profile and that other parameters are for temporary profiles, which is echoed in the schema. The note about 'all parameters are optional' is helpful but already implied by zero required parameters.

  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 action: 'Create a browser session by connecting to an NSTBrowser profile via CDP.' It specifies the resource (browser session) and method (CDP connection), and it is immediately distinguishable from sibling tools like list_sessions, switch_session, and close_session, which perform different operations.

  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 provides explicit guidance: 'Provide profileId to connect to an existing profile, or call with no arguments to create a temporary one.' This tells the agent when to use each invocation mode. It stops short of explicitly naming alternatives, but the sibling context makes the tool's distinct role clear.

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