Server Quality Checklist

Tool Scores

• list_sessionsA
  4.1/5.0
  Behavior3/5

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

  With no annotations provided, the description must disclose behavior, and it does include return structure (a dict with 'sessions' key and summary fields). However, it does not mention sort order, pagination stability, or any potential errors or edge cases. Given the tool is a simple read/list operation, this is 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 well-organized with a clear opening line, then an 'Args' section and a 'Returns' section. Each sentence adds value, and the structure makes it easy to scan. There is no fluff or repetition.

  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 (a list operation with optional filters) and the presence of an output schema, the description covers the key facets: what it does, when to use it, the parameters, and the return shape. It misses minor details like sorting behavior but overall is complete enough for effective use.

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

  Parameters5/5

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

  Schema description coverage is 0%, and the description fully compensates by explaining every parameter (limit, offset, tags, user_email) with enough context: defaults are given, and the purpose of each filter is stated. This goes above and beyond what the raw schema provides.

  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 a specific action ('List Devin sessions') with a resource and purpose ('find sessions by tags or email, or get an overview of recent sessions'). It also mentions usefulness for finding session IDs to inspect or resume, which implicitly distinguishes it from sibling tools like get_session or resume_session, though not naming them explicitly.

  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 clear usage context: 'Use this to find sessions by tags or email, or to get an overview of recent sessions. Useful for finding session IDs to inspect or resume.' This tells the agent when to use the tool, but it does not explicitly state exclusions or describe when to prefer a sibling tool, so it stops short of a 5.

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

• resume_sessionA
  4.3/5.0
  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. It discloses key behavioral traits: sending a message wakes a sleeping session, and the session is monitored until a terminal state. It mentions the return includes status, messages, and metadata, offering useful transparency.

  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 well-structured with a concise summary, usage context, args, and returns. It is slightly longer than necessary due to the extra progress arg and returns description, but each section adds value and the key guidance is front-loaded.

  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 has an output schema, the description doesn't need to explain return values in detail. It covers the main purpose, when to use, wake-up behavior, and monitoring semantics. It lacks details on error handling or timeouts, but is complete enough for selecting and invoking the 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 input schema has zero descriptions, so the description's Args section is essential. It clearly explains session_id and message, and also mentions progress as a dependency, even though it's not in the schema. This adds meaning beyond what the schema provides.

  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 'Send a message to a Devin session and monitor it until completion,' a specific verb+resource+outcome that clearly distinguishes it from siblings like get_session and list_sessions. The purpose is unambiguous.

  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 explicitly states when to use the tool: to resume a sleeping session or send follow-up instructions to a running session. It also explains the wake-up behavior, providing clear context, though it doesn't explicitly exclude alternative tools.

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

• get_sessionA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden. It adds useful context by listing the possible status_enum values (working, blocked, etc.) and clarifies the kind of data returned. It doesn't discuss failure modes or permissions, but for a simple read operation this is reasonably transparent.

  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, usage guidance, an Args section, and a Returns section. Every sentence provides useful information without redundancy, making it appropriately sized and scannable.

  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?

  The description is complete for a simple retrieval tool: it specifies the input, output, and interprets the key status field. It could mention what happens for invalid session_ids or explicitly differentiate from list_sessions, but given the output schema exists and the tool is straightforward, it covers the essential 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?

  The schema only says 'session_id' is a string with no description. The tool description compensates with 'The identifier of the session to retrieve,' which adds clear meaning. Even though schema coverage is 0%, the description fully explains the parameter'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 clearly states the tool's function: 'Retrieve details about an existing Devin session.' It uses a specific verb and resource, and distinguishes from siblings like list_sessions (which lists) and resume_session (which resumes) by focusing on retrieving a single session's details.

  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 when to use the tool: 'Use this to inspect the current status, messages, and metadata of a session' and gives concrete scenarios like checking if a session is running or sleeping. While it doesn't explicitly mention alternatives or exclusions, the context is clear enough for an agent to select it appropriately.

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

• delegateA
  4.6/5.0
  Behavior4/5

  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 does a good job by explaining that the tool monitors until 'finished, blocked, or expired' and that 'progress updates are reported as the session executes.' It also clarifies side effects for parameters like idempotent and unlisted. Minor gaps remain, such as potential long-running behavior or cancellation details, but the core behavior is well covered.

  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 lead sentence, a behavior overview, a clearly formatted Args list, and a Returns section. It is appropriately sized for a tool with 10 parameters: no redundant sentences, each line adds value. The front-loaded purpose makes it easy to scan.

  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 complex tool with 10 parameters, no annotations, and an output schema, this description is thorough. It covers the tool's full lifecycle (creation, monitoring, terminal states), parameter semantics, and what the return contains. It leaves little ambiguity about when to invoke it and what to expect, especially given the rich parameter explanations.

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

  Parameters5/5

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

  The schema descriptions are empty (0% coverage), so the description must fully explain parameters, and it does. Every schema parameter gets a meaningful explanation, and it adds crucial nuances like 'None uses all, empty list uses none' for knowledge_ids and secret_ids. This goes well beyond the schema and fully compensates for the lack of structured descriptions.

  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 clear, specific action: 'Delegate a task to Devin and monitor until completion.' It further explains it creates a new Devin session and monitors it, which succinctly distinguishes it from sibling tools like get_session and list_sessions. The verb and resource are explicit and unambiguous.

  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 when to use the tool: to start a new task and monitor it. It mentions creating a new session and monitoring until a terminal state, which sets expectations. However, it does not explicitly name alternatives or state when not to use it, so it misses the 'explicit exclusions/alternatives' 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.