Server Quality Checklist

Tool Scores

• mychart_screenshotA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds valuable behavioral details: the fallback behavior when idle, the file save location (~/.mychart-mcp/downloads), and the return format { path, url }. These go beyond what annotations convey and help the agent understand side effects and expectations.

  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 concise and well-structured: it opens with the core purpose ('Debug aid: capture a full-page PNG'), then gives a practical use case, and finishes with compact Args and Returns sections. Every sentence earns its place without redundancy.

  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 simple tool with one optional parameter and no output schema, the description is highly complete. It documents the return shape ({ path, url }), the save location, the fallback behavior when idle, and the intended debugging scenario. Nothing essential is missing.

  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 'name' is fully described in the schema as an optional base filename, and the description simply restates it in the Args section. Since schema coverage is 100%, the description adds no additional semantic meaning beyond the schema, so baseline 3 applies.

  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's function: capture a full-page PNG of whatever page the automation browser is currently on, with a fallback to the MyChart home page. It identifies itself as a debug aid and specifies the resource (PNG) and scope, distinguishing it from sibling tools that focus on data retrieval or session 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?

  The description provides explicit context for when to use this tool: 'Useful when list/detail scraping reports nothing recognizable.' This gives a clear scenario. However, it does not explicitly mention when not to use it or alternative tools, so it lacks exclusions that would merit a 5.

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

• mychart_download_test_resultA
  4.5/5.0
  Behavior4/5

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

  Annotations provide readOnlyHint=false, destructiveHint=false, and idempotentHint=true, and the description adds context beyond those: files are saved to a specific directory (~/.mychart-mcp/downloads), the PDF is rendered from the result detail page, and login is required. It also describes the return value shape, which helps the agent understand side effects and outcomes without contradicting the 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?

  The description is compact and well-structured: a one-sentence purpose, a short prerequisites note, a bulleted argument list, a storage location line, and a return shape line. Every sentence contributes meaningful information, and there is no redundant or filler content.

  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 tool with only two parameters, no output schema, and existing annotations, the description covers all essential contextual aspects: what it does, prerequisites, where files are saved, the output format, and how to source the result_id. It does not explain error handling, but that is not necessary for a straightforward download tool of this complexity.

  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 schema already describes both parameters with 100% coverage, so the baseline is 3. The description adds value by specifying that result_id can be a full URL (already in schema) and by giving the default filename pattern ('<date> <test name>.pdf'), which is not in the schema and clarifies how the optional filename parameter behaves.

  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: 'Save one test result as a PDF file on disk,' which clearly states what the tool does and its output format. It also differentiates from siblings by noting the result_id comes from mychart_list_test_results and that it renders from the result detail page, making it distinct from screenshotting or retrieving test result data.

  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 clearly states a prerequisite ('Requires a logged-in session'), which indicates when the tool can be used. It does not explicitly name alternatives or when-not-to-use scenarios, but the context of 'PDF file on disk' and the referenced sibling tools make the appropriate usage clear.

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

• mychart_get_test_resultA
  4.5/5.0
  Behavior5/5

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

  Annotations already declare read-only and idempotent behavior, but the description adds valuable context: the need for a logged-in session, the return format including a truncated flag, and the fallback to download for full PDFs. This goes beyond the annotations and helps the agent understand operational requirements and limitations.

  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 well-organized with separate sections for the main purpose, arguments, and return value. Every sentence provides essential information without fluff, making it easy to parse and understand.

  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 tool with a single parameter and no output schema, the description fully covers what the agent needs: the input source, session requirement, return fields, and truncation handling. It even references the relevant sibling tool for complete PDFs, making it self-contained.

  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 full description of result_id, and the description's Args section repeats the same information. Since schema coverage is 100%, the description adds no new meaning to the parameter beyond what is already structured.

  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 opens one test result and returns full readable content including component values, reference ranges, flags, and provider comments. It distinguishes from siblings like mychart_list_test_results and mychart_download_test_result by focusing on a single result's detailed readable text.

  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 mentions the prerequisite of a logged-in session and points to mychart_download_test_result as an alternative when truncated is true. It also references mychart_list_test_results as the source for result IDs. However, it does not explicitly state when to use this tool versus listing or downloading in all cases, though the context is clear.

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

• mychart_loginA
  4.5/5.0
  Behavior5/5

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

  The description discloses key behaviors: visible browser window, direct user interaction for MFA, no credential passing through MCP, optional prefill from env vars, and persistent profile storage. These traits go well beyond the annotations, which only mark idempotency and open-world behavior.

  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?

  Each section, such as purpose, MFA tip, persistent profile explanation, and parameters, adds necessary context. The description is structured and front-loaded with the core action, making it easy to parse despite its length.

  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 the tool's interactive login nature, the description covers prerequisites, user actions, session persistence, and return format. The explicit Returns line compensates for the missing output schema, and the detail about the browser profile ensures the agent understands side effects.

  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 schema already fully documents timeout_seconds with default 300 and max 900, so the description's Args section repeats this. It adds no new meaning beyond what the schema provides, so baseline 3 applies.

  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: opening a visible browser window at the MyChart login page and waiting for sign-in. This distinguishes it from siblings like mychart_list_test_results or mychart_session_status, which are post-login 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?

  It explains that all other tools work headlessly after this login, implying this is the prerequisite step. It also advises about MFA and session persistence, giving clear when-to-use context, though it doesn't explicitly mention alternatives like checking session status first.

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

• mychart_close_browserA
  4.7/5.0
  Behavior5/5

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

  The description discloses key behavioral traits beyond the annotations: the session is preserved on disk, only the browser process is freed, and the next call auto-relaunches. This adds significant context to the idempotent and non-destructive hints. It also clarifies side effects for the user.

  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 long, front-loaded with the primary action, and contains no fluff. Every sentence adds useful information: the first states the core action, the second clarifies persistence and automatic relaunch.

  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 simple no-parameter tool with no output schema, the description fully covers purpose, side effects, and behavioral guarantees. It addresses the most likely user concerns—whether the login is lost and what happens after closing. Nothing essential 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 no parameters, and schema coverage is 100%, so the baseline for 0 params is 4. The description cannot add more meaning about parameters because none exist, and it appropriately focuses on behavior instead.

  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: 'Close the automation browser' with a specific verb and resource. This is distinct from all sibling tools, which focus on login, test results, and screenshots. There is no ambiguity about what the tool does.

  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 clear context on when to use it: to free the browser process while preserving the login session. It also notes that the next tool call relaunches the browser, implying it can be used between operations. However, it does not explicitly mention when not to use it or alternative tools, though no direct alternative exists among the siblings.

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

• mychart_session_statusA
  4.7/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds valuable behavioral context by stating it 'Runs headless' and disclosing the exact return fields. This goes beyond the structured metadata to inform the agent about the tool's execution mode and output shape.

  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 long, front-loads the core purpose, and packs essential usage and return information without any fluff. Every sentence earns its place.

  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 the tool has no parameters and no output schema, the description fully covers the necessary context: what is checked, the return structure, and the conditional action to take. It leaves no critical gaps for a status-check 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?

  With zero parameters, the baseline is 4. The description doesn't need to explain parameter semantics, but it adds clarity by describing what the tool evaluates and returns, which is sufficient for a no-input status check.

  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 both MyChart provider configuration and browser session login status, with a specific verb and resource. It distinguishes itself from siblings by focusing on the session status and explicitly referencing the mychart_login alternative when loggedIn is false.

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

  Usage Guidelines5/5

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

  The description provides explicit usage guidance: 'safe to call any time' indicates when to use it, and 'If loggedIn is false, run mychart_login' gives a direct alternative action. This clearly orients the agent on when to invoke this tool versus the login tool.

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

• mychart_set_providerA
  4.7/5.0
  Behavior5/5

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

  Annotations indicate idempotentHint=true, readOnlyHint=false, and destructiveHint=false. The description goes beyond this by disclosing that the setting persists to ~/.mychart-mcp/config.json, that URLs are normalized to the instance root, and that changing providers invalidates saved login sessions in a nuanced way. This additional context about side effects and persistence is valuable and not redundant with 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?

  The description is well-structured with a clear opening sentence, an Args section, a Returns statement, and a brief note on persistence. Every sentence serves a purpose, and the length is appropriate for the complexity of the tool. No filler or repetition of schema verbatim.

  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 single-parameter configuration tool, the description fully covers what the tool does, where the setting is stored, what it returns, and the effect on sessions. There is no output schema, but the Returns line describes the normalized base URL. Combined with annotations, this is complete and leaves no open questions.

  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% with the url parameter already described. The description adds meaning by giving concrete examples (e.g., a login page URL), stating that any URL from the provider's site works, and explaining automatic normalization to the instance root. This improves understanding beyond the schema's simple description.

  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-resource pair: 'Configure which health system's MyChart site to use.' This clearly distinguishes it from sibling tools like mychart_login or mychart_list_test_results, as it is the only configuration/setup tool. It also states the need to set it once before logging in, reinforcing its purpose.

  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 'must be set once before logging in,' which tells the agent when to use this tool relative to mychart_login. It also explains that every hospital system runs its own instance, so this setup is required. However, it does not explicitly list alternatives or 'when-not-to-use' scenarios, missing the full bar for a 5.

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

• mychart_list_test_resultsA
  4.9/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, and the description adds valuable context: automatic expansion of lazy-loaded lists, result ordering, the need for an authenticated session, and error handling behavior. No contradiction with 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?

  The description is well-structured with a clear lead sentence, a compact return schema, and an error-handling section. Every sentence adds value and there is no redundancy or 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?

  The description covers the full context: what the tool does, how it behaves (auto-expand, ordering), what it returns (detailed JSON schema), prerequisites (login), and failure paths (screenshot fallback). Given the tool's moderate complexity, this is 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?

  There are zero parameters (input schema is empty), so the baseline is 4. The description doesn't need to add parameter meaning because there are none; it wisely focuses on the return schema and behavior instead.

  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 ('Fetch') and resource ('full list of test results from the MyChart portal'), clearly distinguishing it from siblings like mychart_get_test_result and mychart_download_test_result. It also specifies content types (labs, imaging, pathology) and ordering.

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

  Usage Guidelines5/5

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

  Explicitly states the prerequisite of a logged-in session and instructs to run mychart_login if not logged in. Also provides a fallback to mychart_screenshot if no results are recognized, effectively guiding when to use this tool versus alternatives.

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