Server Quality Checklist

Tool Scores

• generate_deploymentA
  4.2/5.0
  Behavior3/5

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

  With no annotations, the description must carry the disclosure burden. It does state the side effect (writes prefect.yaml), the file's key contents (YAML anchors, schedule config, TODO stubs), and the return shape. However, it doesn't disclose overwrite behavior, permissions, or failure modes, leaving important behavioral ambiguity for a file-writing 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 compact and structured with intro, Args, and Returns sections; no sentence is filler. The 'Call after generating flow.py' line adds a critical usage cue without wasting words.

  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 3-parameter code-generation tool with a nested flows structure, the description covers inputs, output, and pipeline timing. It could strengthen completeness by specifying file-handling behavior (e.g., overwrites) and providing a minimal example, but it is sufficient for a typical invocation.

  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 description coverage is 0%, so the description compensates by documenting all three parameters. It explains the required flow fields (flow_name, entrypoint) and optional fields (schedule, parameters, etc.) and gives the workspace default, adding real meaning beyond the bare schema.

  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?

  Opens with a specific verb phrase 'Write prefect.yaml deployment configuration from DAG metadata,' clearly naming the deliverable and source. The sibling tools have distinct purposes, and 'Call after generating flow.py' further distinguishes this as the deployment-config generation step.

  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?

  States an explicit precondition ('Call after generating flow.py'), giving clear context for when to invoke. It does not name alternatives or state when not to use, 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.

• search_prefect_docsA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description must disclose behavior itself. It does so by stating it returns 'search results or an error with suggestion to run 'colin run'', which covers expected outcomes and error handling. The 'real-time' mention implies network dependability, though it does not elaborate on latency or side effects. This is reasonable transparency for a simple 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 is concise and well-structured with separate Args and Returns sections. Each sentence serves a purpose, from the main action to the usage context and output behavior. There is no filler, making it easy for an agent to parse quickly.

  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 tool with one parameter and an output schema, the description covers the essentials: what it does, when to use it, and what to expect. The mention of 'Prefect MCP server' and 'colin run' adds context, though the meaning of 'colin' is not explained. Overall, it is sufficiently complete for an agent to invoke the tool correctly.

  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 has one parameter 'query' with no description (0% coverage). The description compensates by including an Args section that explains 'query: Search query for Prefect docs.' This adds meaning beyond the schema, but it is minimal—no format, examples, or constraints are given. This is adequate for a simple string parameter but not exemplary.

  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 'Search current Prefect documentation' with a specific verb and resource. It distinguishes itself from sibling tools like read_dag or lookup_concept, which serve different purposes. The addition of 'real-time queries beyond what Colin pre-compiled' further clarifies the tool's 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 Guidelines4/5

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

  The phrase 'For real-time queries beyond what Colin pre-compiled' provides a clear context for when this tool should be used. It implies a dynamic search scenario and hints at a fallback via 'colin run'. However, it does not explicitly discuss exclusions or alternative tools, so it falls short of a perfect score.

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

• lookup_conceptA
  4.5/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It discloses that it searches 'Colin-compiled knowledge' and falls back to built-in mappings if Colin output is unavailable, and it also explains the return structure. This goes beyond a simple lookup description by revealing the source and fallback 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 well-structured with a front-loaded purpose sentence, a brief behavioral note, and a clear Args/Returns docstring. Every sentence contributes useful information without fluff, making it appropriately sized and easy to scan.

  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 low complexity (one param, output schema present), the description is largely complete. It explains what the tool does, what the concept parameter means, and what the return contains. The only minor gap is the lack of explicit usage boundaries relative to siblings, but this does not detract significantly from overall completeness.

  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 coverage is 0%, so the description must compensate. It fully explains the single 'concept' parameter, provides examples ('PythonOperator', 'XCom', 'TaskGroup', 'postgres_default'), and clarifies that it expects an Airflow concept. This is excellent parameter documentation beyond the bare schema.

  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 begins with a specific verb+resource: 'Look up Airflow→Prefect translation knowledge for a concept.' This clearly distinguishes it from sibling tools like search_prefect_docs (which likely searches docs) and read_dag (which reads DAGs). The scope 'for operators, patterns, connections, and core concepts' further clarifies 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 Guidelines4/5

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

  The description provides clear context on what the tool covers (operators, patterns, connections, core concepts) and mentions the fallback behavior, implying when it is appropriate to use. However, it does not explicitly name alternatives or state 'when not to use', so it lacks the explicit exclusion/alternative guidance of a 5.

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

• read_dagA
  4.5/5.0
  Behavior4/5

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

  No annotations are supplied, so the description carries full responsibility for behavioral disclosure. It explicitly lists accepted inputs (path/content), returned fields (source, file_path, file_size_bytes, line_count), and an error possibility. While it doesn't mention potential edge cases (e.g., file-not-found, mutual exclusivity of params), it is transparent for a read-only operation.

  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 logically structured: a clear purpose statement, a brief note on accepted input forms, then Args and Returns sections. Every sentence earns its place; no filler or 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 read tool with an output schema, the description is complete: it states what it does, what inputs it accepts, what it returns, and that it can error. The output schema covers the return structure, and the description enumerates the key fields. No important information is missing given the tool's straightforward nature.

  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 no parameter descriptions (0% coverage), so the description's Args section is essential. It defines path as 'Path to a DAG file on disk' and content as 'Inline DAG source code', adding meaning beyond the bare parameter names. It stops short of specifying mutual exclusivity or expected content format, but it provides adequate semantic grounding.

  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 'Read an Airflow DAG file and return raw source with metadata' – a specific verb, resource, and expected output. This distinguishes it from sibling tools like lookup_concept or generate_deployment, 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 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 this tool (whenever you need to read a DAG file's source or inline code) but lacks explicit alternatives or exclusions. Sibling tools are conceptually different, so confusion is unlikely, but no direct 'use this instead of X' guidance is provided.

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

• generate_migration_reportA
  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 full behavioral burden. It discloses the write side effect (MIGRATION.md), describes the produced checklist, mentions doc links, and notes a suggestion to add the Prefect MCP server. It does not explicitly address overwrites or file permissions, but the core behaviors are 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 dense but well-structured: a one-line purpose, a usage positioning sentence, and organized Args/Returns sections. Every sentence adds meaningful information, and the length is justified by the need to document five parameters and return fields.

  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 complexity (5 params, no annotations, no schema descriptions), the description is remarkably complete. It covers purpose, when to call it, parameter semantics, and return value shape. The presence of an output schema means the return format does not need further elaboration.

  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%, so the description must compensate. The Args section explains every parameter, including the structure of the 'decisions' list and the meaning of 'manual_actions'. This fully bridges the gap left by the bare schema.

  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: 'Write MIGRATION.md — human-readable record of a DAG conversion.' It distinguishes itself from siblings by stating it is the final step after generate_deployment and focuses on documentation/reporting rather than transformation or validation.

  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 instructs 'Call as the final step after generate_deployment,' providing clear when-to-use context. It does not list exclusions or direct alternatives, but the pipeline positioning sufficiently clarifies its role relative to siblings.

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

• scaffoldA
  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 full behavioral disclosure. It states it creates a project skeleton, lists the parameter effects, and specifies the return format (JSON with created_directories, created_files, etc.). It does not mention overwrite behavior or error handling, which are potential gaps, but overall it provides substantial transparency.

  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 and front-loaded: a one-sentence purpose, a critical exclusion note, a bulleted Args list, and a Returns summary. Every sentence is informative, with no filler or 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?

  Given the tool's complexity (7 parameters, no annotations, no schema descriptions), this description is remarkably complete. It covers the main purpose, non-goals, all parameter semantics, and return value shape. The only minor omission is explicit usage alternatives, but the overall context is sufficient for an agent to select and invoke the tool correctly.

  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 has 0% description coverage, so the description must compensate. It does so comprehensively, listing all 7 parameters with meaningful explanations, including defaults (project_name defaults to directory name), structural purpose (workspace for deployments/<workspace>/ structure), and format hints for schedule_interval (cron string, preset, seconds, or None). This adds significant value beyond the bare schema.

  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: 'Generate a Prefect project directory structure.' It further clarifies scope by stating it follows prefecthq/flows conventions and explicitly excludes flow code generation, making its purpose unambiguous and distinct from the sibling tool 'generate_deployment'.

  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 use by stating what it does NOT do ('Does NOT generate flow code - that's for the LLM to do'), which guides the agent away from using it for code generation. It does not explicitly name alternatives among the sibling tools, but the exclusion and focus on scaffolding imply appropriate usage.

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

• validateA
  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 clearly states that the tool returns both source files and syntax check results, and that the agent must perform the structural comparison. It also lists the exact return fields, which is valuable behavioral context, though it does not cover error handling 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?

  The description is concise, front-loaded with the main purpose, and uses a clear Args/Returns structure. Every sentence earns its place, and there is no fluff or 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?

  The description provides all necessary context for the agent to understand what the tool does, what inputs to provide, and what outputs to expect. It also explicitly assigns the responsibility of structural comparison to the agent, which is critical for correct usage. The presence of an output schema reduces the need for more return-value detail.

  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 provides only type 'string' for both parameters with no descriptions, but the description adds crucial semantics by stating each is a 'Path or inline content' for the original DAG and the generated flow. This fully compensates for the 0% schema description coverage.

  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: 'Validate a converted Prefect flow against the original Airflow DAG.' This clearly distinguishes the tool from siblings like 'read_dag' and 'scaffold', and states the exact scope of the operation.

  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 (when validating a converted flow against its original DAG) and instructs the agent on the next step: 'You perform the structural comparison.' However, it does not explicitly mention alternatives or when not to use this tool, so it stays just below a perfect score.

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