Server Quality Checklist

Tool Scores

• instagram_disconnectA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare destructive and not read-only. The description adds specific context beyond annotations: it closes Chromium, permanently deletes the profile, and removes locally derived account and relationship data. This clarifies exactly what is destroyed without contradicting annotations.

  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?

  One concise sentence at 17 words, front-loaded with the main action ('Closes Chromium') and followed by the destructive scope. Every word earns its place with no filler.

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

  Completeness5/5

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

  For a zero-parameter tool with an output schema, the description adequately covers the side effects (closing Chromium) and the full scope of data deletion. It provides enough information for an agent to decide to invoke it without needing return-value details.

  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 has zero parameters, and the schema has no properties. The baseline for zero parameters is 4, and the description does not need to add parameter details. No deduction necessary.

  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 states a specific action: closes Chromium and permanently deletes the Instagram browser profile plus locally derived account and relationship data. This clearly distinguishes it from siblings like instagram_connect and instagram_get_non_followers, which serve different purposes.

  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 does not explicitly state when to use this tool or mention alternatives. The verb 'disconnect' implies usage for disconnecting, but there is no explicit guidance comparing it to connect/status tools. Usage is only implied.

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

• instagram_connection_statusA
  4.4/5.0
  Behavior4/5

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

  The description adds context by stating it 'reports the current login or session state' and 'never asks for credentials,' providing safety-relevant behavior beyond the annotations. Annotations already hint at idempotency and non-destructiveness, and the description does not contradict them.

  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, front-loaded with the primary use case. Every sentence adds value: one tells when to use it, the other clarifies what it reports and that it doesn't ask for credentials. No redundancy.

  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 tool's simplicity (no params) and the presence of an output schema, the description adequately covers the core behavior and usage context. It mentions the important LOGIN_PENDING scenario and the credential-avoidance behavior, providing sufficient completeness for an AI agent.

  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 has zero parameters, and the input schema confirms this with 100% coverage. The description does not need to add parameter semantics, and per the rubric, a tool with 0 params receives a baseline of 4, which is appropriate here.

  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 checks whether Instagram is connected and reports the current login/session state. This specific verb+resource combination distinguishes it from sibling tools like instagram_connect and instagram_disconnect.

  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 explicitly says to use this when checking connection status, especially after instagram_connect returned LOGIN_PENDING. It provides clear context but does not explicitly state when not to use it or mention alternatives beyond the implied distinction from connect/disconnect.

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

• instagram_get_non_followersA
  4.5/5.0
  Behavior5/5

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

  The description discloses key behavioral traits: it fetches a complete Following list before classification, reports unknown statuses, caches normalized results locally, and paginates MCP output. These go well beyond the annotations, which only indicate readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false. The caching detail aligns with the readOnlyHint=false, and the pagination is useful context.

  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, dense sentence that front-loads the core purpose and then adds behavioral context in one sweep. Every clause contributes information without redundancy, making it both concise and structured.

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

  Completeness5/5

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

  With a full input schema, an output schema, and annotations, the description still adds necessary context: the complete fetch, local caching, unknown statuses, and pagination. This covers the operational behavior and potential performance implications, making it complete for an AI agent.

  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 baseline is 3. The description does not add parameter-specific semantics, but it mentions pagination and caching, which indirectly relate to the cursor and refresh parameters. Since the schema already fully documents each parameter, the description adds marginal value but does not need to 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 opens with a specific verb and resource: 'Returns accounts the connected user follows that explicitly do not follow the user back.' This clearly states what the tool does and differentiates it from sibling tools like instagram_connect and instagram_disconnect, which are about connection management.

  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?

  While there is no explicit 'use when' or exclusion statement, the description makes the tool's purpose unambiguous and its context (Instagram non-followers) clear. The sibling tools are distinct, so the intended usage is evident even without an explicit alternative pointer.

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

• instagram_connectA
  4.7/5.0
  Behavior5/5

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

  The description reveals concrete behaviors beyond the annotations: reuse of a verified saved session, opening a dedicated local Chromium profile, returning immediately with LOGIN_PENDING, and requiring credentials to be entered only on instagram.com. These details significantly enrich the agent's understanding of what happens when invoked.

  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 three sentences, front-loaded with the usage condition, and every sentence contributes unique information (when to use, what happens, where credentials go). No redundancy or unnecessary detail.

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

  Completeness5/5

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

  Given that the tool has no parameters and an output schema exists (which likely documents the return structure), the description covers all essential contextual aspects: session reuse, browser launch, immediate LOGIN_PENDING, and the required follow-up action with instagram_connection_status. It is complete for a connection-initiating tool.

  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, so there are no parameter details to add. With 0 params, the baseline is 4, and the description appropriately does not attempt to explain parameters, making it fully sufficient.

  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 opens with a specific use case: 'Use this when the user wants to connect Instagram or resume an unfinished local login.' It clearly identifies the resource (Instagram) and the action (connect), and distinguishes itself from sibling tools by noting that the user should 'then use instagram_connection_status' for status checks.

  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?

  It provides an explicit trigger condition ('Use this when...') and instructs the user to follow up with instagram_connection_status. However, it does not explicitly state when not to use this tool or directly compare with alternatives like instagram_disconnect or instagram_get_non_followers, so it's clear but lacks explicit exclusions.

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