Server Quality Checklist

Tool Scores

• search_messagesB
  3.3/5.0
  Behavior2/5

  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 only states the basic search operation and does not reveal how filters combine, what the return format is, whether it returns full messages or metadata, or any other runtime behaviors. This is a significant gap for a search 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 consists of a single, tight sentence that is front-loaded with the action and resource. It is concise and free of unnecessary words, making it easy for an agent to quickly grasp the tool's core purpose.

  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?

  For a tool with 5 parameters, no required fields, no output schema, and only 60% schema description coverage, the description is insufficient. It does not explain the meaning of all parameters, the behavior of filters in combination, or what a successful search returns. This leaves the agent with many unknowns.

  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?

  The description lists three filter criteria (sender, subject, body text) that map to the from, subject, and text parameters. However, the schema already provides descriptions for these fields, so the description adds no new meaning. It omits the limit and mailbox parameters entirely, leaving those without any description to compensate for schema gaps.

  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: searching a mailbox by sender, subject, or body text. It uses a specific verb and resource, and the criteria distinguish it from list_messages (which lists without search) and get_message (which retrieves a single message).

  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 the tool is for searching messages with specific filters, but it does not explicitly state when to use this tool over list_messages or get_message, nor does it mention any exclusions or alternative tools. The context is implied by the search criteria but not elaborated.

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

• get_messageA
  3.5/5.0
  Behavior3/5

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

  No annotations were provided, so the description carries the transparency burden. It states the tool 'Fetch' (implying a read operation) and describes the return content, but it does not disclose error behavior, permission requirements, or explicitly confirm that it has no side effects beyond the verb choice.

  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, front-loaded sentence that directly states what the tool does without unnecessary words or repetition.

  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?

  Even though the tool is simple, the description omits the mailbox parameter's semantics, provides no guidance on how to obtain a UID, and does not mention error cases. An agent would need to infer or guess several operational details, making the description incomplete for confident invocation.

  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%. The description explains 'UID' as the identifier but does not mention the 'mailbox' parameter at all, leaving its purpose and default value undocumented. This is a clear semantic gap for one of two 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 uses a specific verb ('Fetch'), names the resource ('full parsed content (text/html body)'), and scopes it to a 'single message by UID.' This clearly distinguishes it from siblings like list_messages and search_messages.

  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: you need a UID to fetch a message's content, which you would obtain from list_messages. However, it does not explicitly state when to prefer this tool over siblings or provide any exclusions or alternative mentions.

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

• list_messagesA
  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 burden of disclosing behavior. It states that messages are listed newest first and defaults to INBOX, implying a read-only operation, but does not mention pagination, whether messages are marked as read, or any authentication/error 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?

  The description is a single, front-loaded sentence with no filler. Every word adds value, and it covers the essential behavior, order, and default.

  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 tool with two optional parameters and no output schema, the description is mostly complete: it states the action, resource, ordering, and default mailbox. It could be improved by briefly explaining the limit parameter and pointing to alternatives, but it is adequate as-is.

  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?

  The input schema already documents the mailbox parameter and the limit's numeric constraints, but the description adds no extra meaning for 'limit' beyond 'most recent'. Schema description coverage is only 50%, so the description should compensate for the undocumented limit behavior, but it does not.

  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 ('messages'), clearly distinguishes this from siblings like list_mailboxes and get_message, and adds useful scope: mailbox default INBOX and order newest first.

  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 for when to use this tool: to list recent messages with a default mailbox. It does not explicitly mention alternatives or when not to use it, but the intended use case is clear enough for most scenarios.

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

• list_mailboxesA
  4.1/5.0
  Behavior2/5

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

  No annotations are provided, so the description must disclose behavioral traits. It only states that it 'lists' mailboxes, which implies a read operation but provides no details about return format, ordering, potential errors, or whether system/hidden folders are included. The description carries minimal behavioral information.

  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, focused sentence with no wasted words. It is front-loaded with the action and resource, and every word contributes to meaning.

  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, no-output-schema, simple listing tool, the description is complete enough. It specifies the scope (all mailboxes on the account via Bridge) and the absence of parameters means there is no additional input context needed. The tool's function is fully captured.

  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 is empty, so the schema provides complete coverage. The description adds no parameter-specific meaning, but the baseline for zero parameters is 4, which is appropriate.

  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 verb ('List'), a clear resource ('mail folders/mailboxes'), and scope ('all... on the Proton Mail account via Bridge'). It clearly distinguishes from sibling tools that deal with messages (list_messages, search_messages, get_message).

  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 implies this tool is for enumerating mailboxes, and the context provided by sibling tool names (message-focused) makes the appropriate use case evident. It doesn't explicitly state exclusions or alternatives, but the distinction is clear from the naming.

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