Server Quality Checklist

Tool Scores

• monday_list_updatesA
  3.8/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is known. The description adds useful details: ordering (newest first) and inclusion of replies. It does not describe pagination, return format, or error behavior, but with annotations covering the read-only nature, this is acceptable.

  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. It starts with 'Returns the updates' and immediately conveys the primary action and resource. No wasted words; every phrase adds value (e.g., 'newest first, with their replies' is useful behavioral detail).

  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 read tool with two well-documented parameters and read-only annotations, the description is adequate. It explains what is returned (updates, replies, ordering) and the title clarifies the use case. It lacks pagination details, but the schema covers the limit parameter. Given the low complexity, this is complete enough.

  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% (both limit and item_id have descriptions). The description adds no parameter-specific information beyond what the schema provides. Since the schema already documents defaults and types, the baseline of 3 applies.

  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 the tool returns updates, which are the item conversation, newest first, with replies. This is a specific verb+resource ('returns updates') and clarifies the scope (item conversation). However, it does not explicitly distinguish itself from sibling tools like monday_create_update, though the name and context imply the read nature.

  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: use this to read the conversation on an item. The title 'Read the conversation on an item' reinforces this. It does not mention exclusions or name alternatives, but the existence of monday_create_update for writing implies the read use case. This is clear context without explicit when-not-to-use guidance.

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

• monday_create_itemA
  3.9/5.0
  Behavior3/5

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

  The description goes beyond annotations by explaining that 'This server converts them to the JSON that monday.com stores,' disclosing a non-obvious server-side transformation. Annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) are sparse and not contradicted. However, it does not detail error behavior, return values, 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?

  Three short sentences that front-load the purpose, then explain value formatting, and end with a prerequisite. Every sentence adds information and no fluff.

  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 create tool with 5 parameters and a nested `values` object, the description covers the core usage and prerequisite. It does not mention return value or error handling, but no output schema exists, so those details are less critical. The description is solid and sufficiently complete for the 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?

  Schema coverage is 100% with descriptions for all parameters. The description adds crucial meaning for the `values` parameter: keys can be column id or title, values should be plain (e.g., 'Done', '2026-08-14'), and the server converts them. This is more specific than the schema's example.

  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 states a specific verb and resource: 'Creates one item on a board.' This clearly distinguishes it from update/delete/subitem tools, though it does not explicitly name an alternative. The wording is unambiguous and informative.

  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?

  Provides a clear prerequisite: 'Call monday_get_board first to see the columns.' This gives the agent a concrete step for using the tool correctly. It implies the tool is for adding new items to a board, but does not explicitly mention when not to use it or alternatives like monday_create_subitem.

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

• monday_create_updateA
  4/5.0
  Behavior4/5

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

  The description discloses non-obvious behaviors: the body accepts simple HTML and followers receive notifications. Annotations already convey the write/non-idempotent/non-destructive nature, so the description adds useful side-effect 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?

  Two concise sentences: one for the action, one for the input format and side effect. No wasted words, front-loaded with the primary verb.

  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 write tool with comprehensive annotations and full schema coverage, the description is reasonably complete. It covers purpose, input constraints, and a key side effect. Lacks prerequisites or return value, but those are not essential given the schema and annotations.

  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 covers 100% of parameters with descriptions for body (including HTML allowance) and item_id. The description does not add substantial meaning beyond the schema, so baseline 3 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 clearly states the tool adds an update to the item conversation, using the specific verb 'adds' and identifying the resource. It distinguishes from siblings like monday_list_updates (read) and monday_update_item (modify item fields).

  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 when you want to post a new update to an item's conversation, but it does not explicitly contrast with alternatives or state when not to use it. The notification detail provides context but not explicit guidance.

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

• monday_list_usersA
  4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, covering the safety profile. The description adds use-case context but does not disclose additional behavioral traits such as pagination limits, default filtering behavior, or how 'all_pages' affects results. It provides some value beyond annotations but lacks rich behavioral detail.

  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?

  Two short sentences, front-loaded with the main action, no redundant phrasing. The use case sentence is concise and valuable.

  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 tool is a straightforward list operation with all parameter details fully in the schema. The description's use-case hint (mapping names to IDs) helps the agent understand the return value's purpose. No output schema exists, but for a simple list tool the description is adequate. It could mention pagination behavior, but the schema's 'all_pages' parameter covers that.

  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 has 100% description coverage for all five parameters, including defaults and meanings. The description adds no additional parameter-level semantics, so the baseline score of 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 uses a specific verb 'Lists' with a clear resource 'people in the account', and adds a concrete use case (turning a name into a numeric user ID for people columns). It clearly distinguishes from sibling tools that operate on workspaces, boards, items, etc.

  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 a specific scenario ('Use it to turn a name into the numeric user id that a people column needs'), giving clear context for when to use this tool. It does not explicitly state when not to use it or name alternatives, but sibling tools are all for different resources, so ambiguity is low. Slight deduction for lacking explicit exclusions.

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

• monday_list_workspacesA
  4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, so the safety profile is known. The description adds minimal context beyond listing workspaces and the linkage to list_boards, but does not mention pagination, ordering, or other behavioral details. 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?

  Two sentences, each earning its place: first states the core purpose, second gives a practical usage hint. No filler or 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 simple nature of the tool, the readOnlyHint annotation, and the 100% schema coverage, the description covers the essentials. It explains the output's purpose (workspace ids) through the usage hint. Minor absence: does not explicitly mention that the account context is the default scope, but this is implied by 'in the account.'

  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 provides 100% coverage for the single 'limit' parameter with description 'Default 50.' The tool description does not add any additional meaning about this parameter, so the baseline of 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 lists workspaces in the account, using a specific verb and resource. It also distinguishes itself from sibling tools by noting how the resulting workspace id can be used to narrow monday_list_boards.

  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 a clear usage hint: use a workspace id to narrow monday_list_boards. This implies when the tool is useful, though it does not explicitly mention when not to use it or alternatives beyond the sibling context.

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

• monday_move_itemA
  4/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the constraint 'on the same board', which is useful, but it does not disclose any additional behavioral traits such as side effects or restrictions. 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 a single, concise sentence that directly states the action and scope. It avoids unnecessary detail and is front-loaded with the core purpose.

  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 simple operation, the presence of annotations, and full schema coverage, the description is largely complete. It does not explain the return value, but no output schema exists and the tool's behavior is straightforward. Minor omissions like what happens on failure or whether the group param accepts id vs title are already covered by the schema.

  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 provides 100% coverage with descriptions for both parameters (item_id and group). The tool description adds no additional parameter-level meaning beyond what the schema already provides, so the baseline score of 3 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 uses a specific verb ('Moves') and resource ('one item into another group on the same board'), clearly distinguishing it from sibling tools like create_item, update_item, and delete_item. The scope is 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 states what the tool does, giving the context for when to use it (moving an item to a group on the same board). It does not explicitly mention alternatives or when not to use it, but 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.

• monday_update_itemA
  4/5.0
  Behavior3/5

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

  Annotations already indicate readOnly=false, idempotent=true, and destructive=true. The description adds context by noting that values use the same plain form as monday_create_item, and that the item name is only changed when 'name' is given. However, it does not disclose specifics about side effects, overwriting behavior, or handling of missing items, going beyond the annotation summary.

  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 with no fluff. The first sentence front-loads the primary purpose, and the second concisely adds the format detail. Every word earns its place, making it highly efficient.

  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 5 parameters and a nested object, the description, schema, and annotations collectively provide sufficient context for usage. The description covers the main behavior, the schema defines all parameters, and annotations indicate safety profile. The reference to monday_create_item for value format adds completeness. Minor gap: no explicit mention of behavior when item_id doesn't exist, but this is not critical.

  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 descriptions cover all 5 parameters (100% coverage). The description adds value by explaining that the 'values' parameter uses the same plain form as monday_create_item, which helps users understand the expected structure. It also clarifies the conditional nature of the 'name' parameter. This enriches the basic schema explanations.

  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 that the tool changes the columns of a single item and optionally the item name. The verb 'changes' is specific, and the resource (item columns) is well-defined. It distinguishes itself from sibling tools like create, delete, and move by focusing on modification of existing item columns.

  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?

  Usage is implied: this tool is for updating an existing item, as opposed to creating or deleting. It does not explicitly state when to use it versus alternatives, nor does it provide exclusions or conditions. The reference to monday_create_item for value format hints at relatedness but does not offer selection guidance.

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

• monday_list_boardsA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint, so safety context is covered. The description adds behavioral details: 'newest use first' ordering and that search filters on name (per schema), plus the importance of returned board IDs. It does not describe the return format fully, but with no output schema, the ID mention provides 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 three concise sentences with no redundant words. Every sentence adds distinct information: listing behavior, name search, and the ID prerequisite.

  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 tool is a straightforward list operation with full schema coverage and safe read annotations. The description communicates the core purpose and the key return value (board IDs). It could be slightly more explicit about the full return structure, but the combination of schema and description is adequate for an agent to select and invoke it.

  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 description does not need to duplicate parameter details. It does mention using `name` for searching, but that merely restates the schema's description. No additional semantic value is added for page, limit, or workspace_id.

  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 the specific verb 'Lists' with the resource 'boards', and adds distinctive traits: 'newest use first', name search capability, and that results carry board IDs needed by other tools. This clearly differentiates it from sibling tools like monday_get_board or monday_list_workspaces.

  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 implies usage as a prerequisite: 'The result carries board ids, which every other tool needs.' This tells the agent to use this tool first to discover board IDs before calling other monday.com tools. However, it does not explicitly name alternatives or exclusions, so it stops short of a full 5.

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

• monday_list_itemsA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint, and the description adds that results are paginated via cursor, filters are applied, and column values are rendered as readable text. This gives useful behavioral context beyond the schema, though it doesn't discuss rate limits or detailed response structure.

  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-loading the core behavior and then adding the prerequisite and pagination note. Every sentence earns its place with no wasted 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 read-only paginated listing tool, the description captures the essential flow: board scoping, readable column values, filtering, and cursoring. The lack of an output schema is mitigated by the 'readable text' mention, and the prerequisite to get board metadata is included. It could be more explicit about alternative tools, but overall it's sufficient.

  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 schema already documents all six parameters. The description adds minimal extra value by mentioning filters and cursor for pagination, but it doesn't explain group, limit, or search beyond their schema 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 clearly states the tool returns a page of items from a single board with column values as readable text, using a specific verb and resource scope. It also distinguishes from broader listing tools by emphasizing 'from one board' and the readable-text transformation.

  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 advises calling monday_get_board first to learn column ids and labels, which is a clear prerequisite. However, it does not explicitly name alternative tools like monday_get_items or state when to avoid this tool, so differentiation is left mostly to inference.

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

• monday_get_boardA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint, so the safety profile is known. The description adds meaningful context by disclosing what the response contains (groups, columns, label values) and the rationale for calling it before mutations. This goes beyond just restating the annotation hints, though it doesn't mention caching behavior (which is in the schema description) or other edge cases.

  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: the first states the function and output, the second provides usage guidance. Every word contributes value, and it is front-loaded with the essential purpose. There is no redundancy or fluff.

  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 read-only retrieval tool with well-documented parameters and annotations, the description is complete. It explains what data is returned (groups, columns, labels), the scope (one board), and when to invoke it. Since there is no output schema, the description sufficiently covers the return content without needing to enumerate every field.

  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 description coverage is 100%, with both parameters ('refresh' and 'board_id') fully documented. The tool description itself does not add any additional meaning about the parameters, so it relies on the schema. The baseline of 3 is appropriate since the schema does the heavy lifting and the description adds no extra parameter context.

  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 returns 'the groups and the columns of one board' with the labels for status and dropdown columns, which is a specific verb+resource. It distinguishes itself from sibling tools like monday_list_boards (which lists boards) and monday_get_items (which gets items), and emphasizes it operates on a single board.

  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 states when to use the tool: 'Call this before you create or change an item,' and explains why ('a column value must match its column type'). This gives clear context, but it does not mention when not to use it or identify alternatives, 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.

• monday_get_itemsA
  4.3/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=true and openWorldHint=true. The description adds useful behavioral context by specifying what data is returned (every column, with id, readable text, and stored JSON). No contradictions 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 two concise sentences: the first states the function and output format, the second provides usage context. No wasteful or redundant text.

  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 read-only tool with a single, well-documented parameter and no output schema, the description provides a complete picture: what it returns, when to use it, and safe operation via annotations. The return format is specified, so the agent can interpret results.

  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 fully describes the parameter 'item_ids' with 'Numeric item ids. Up to 100 at a time.' (100% coverage). The description adds no further parameter semantics, 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 returns every column of one or more items, with specific output details (column id, readable text, stored JSON). This distinguishes it from sibling tools like monday_list_items, which likely provides a lighter list view.

  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?

  Provides explicit guidance: 'Use it before you change an item.' This establishes when to invoke the tool but does not explicitly name alternative tools or exclusions, so it falls short of a full 5.

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

• monday_create_subitemA
  4.4/5.0
  Behavior4/5

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

  Annotations already mark readOnlyHint=false and destructiveHint=false, covering the mutation safety profile. The description adds valuable behavior: 'Column values apply in a second step, because a subitem lives on its own hidden board.' This explains a non-obvious trait that column values are not set immediately, going beyond the annotations. No contradiction.

  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 core action and followed by a concise behavioral note. Every word earns its place, with no redundant details or repetition of schema fields.

  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 moderate complexity, the description covers the main purpose, the crucial caveat about column values, and the hidden-board rationale. It lacks explicit return value details, but there is no output schema, and for a create operation this is often implied. The descriptions and annotations together provide sufficient 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?

  Schema description coverage is 100%, so baseline is 3. The description adds meaning to the 'values' parameter by explaining why column values are not applied immediately, which helps the agent understand the parameter's optionality and timing. It does not reformat the schema but enriches the semantic context.

  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 purpose: 'Creates a subitem under a parent item.' This uses a specific verb and resource, distinguishing it from the sibling 'monday_create_item' which creates top-level items. The additional note about column values applying later further clarifies its specific 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 implies usage context by explaining that column values are not applied immediately due to the subitem's hidden board. This clues the agent that a second step is needed, but it does not explicitly name alternatives or when to choose this over 'monday_create_item'. Clear context with no exclusions, hence a 4.

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

• monday_get_meA
  4.4/5.0
  Behavior4/5

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

  Annotations already signal read-only and open-world behavior. The description adds value by explaining that the tool proves connectivity, maps the token to a user, and reveals the account slug, which are non-obvious behavioral details.

  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: the first states what the tool returns, the second gives actionable usage guidance. There is zero redundancy and the key information 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?

  With no output schema and no parameters, the description conveys the return focus and intended first-use scenario. It could mention specific returned fields or response format, but the existing detail is sufficient for a simple identity/connectivity check.

  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 schema coverage is effectively complete, so the description adds no parameter details. This matches the baseline for parameterless tools.

  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 returns the user behind the API token and its account, which precisely identifies the tool's purpose. It is distinct from sibling tools that list workspaces, boards, or items, focusing instead on token identity.

  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 advises calling this first to verify the connection and learn the account slug, providing clear usage context. It does not mention alternatives or when not to use it, but the guidance is concrete and situationally specific.

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

• monday_graphqlA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds context beyond annotations by explaining this is a raw GraphQL interface with no column value translation, and that mutations are possible. It does not detail error behavior or rate limits, but the annotation coverage lowers the bar.

  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 exactly two sentences, front-loaded with the core purpose, then immediately followed by usage boundaries. Every sentence earns its place with zero redundancy or filler.

  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 raw GraphQL tool with no output schema, the description covers the essential context: purpose, when to use, and why to prefer other tools for item work. It does not explain return format or error handling, but GraphQL responses are self-descriptive and the open-ended nature is noted by annotations (openWorldHint=true).

  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% (query and variables both have descriptions), so the baseline is 3. The description does not add extra semantic detail about the parameters themselves, but the context about column value translation hints at why variables may differ from other tools. No significant added value beyond the 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 clearly states the tool 'Sends a GraphQL query or mutation straight to the monday.com API', which is a specific verb+resource. It also distinguishes itself from siblings by explicitly noting it is for 'something the other tools do not cover', situating its purpose relative to the other tools.

  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 gives explicit when-to-use guidance ('Use it only for something the other tools do not cover, such as boards, docs or webhooks') and when-not-to-use guidance ('prefer them for item work' because other tools handle column value translation). This is a model of usage clarity.

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

• monday_delete_itemA
  4.7/5.0
  Behavior5/5

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

  Discloses that archiving is undoable in the monday.com UI while delete removes the item permanently and requires confirm=true. This adds important safety and reversibility context beyond the destructiveHint annotation.

  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?

  Two concise sentences, front-loaded with the default behavior, with no fluff or redundancy. Every phrase 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?

  For a destructive operation with no output schema, it fully communicates default behavior, undoability, permanent deletion, and the confirm requirement. The schema and annotations cover the remaining parameter 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?

  Schema coverage is 100%, so baseline is 3. The description enhances mode semantics by explaining the real-world effect of archive vs delete and the confirmation requirement, adding meaningful context beyond the 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?

  States it archives an item by default and can permanently delete the item with mode=delete. Clearly distinguishes from sibling tools by being the removal/archival operation rather than update or move.

  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?

  Explicitly says archive is the default and delete should only be used when the user asks, with confirm=true. Does not name alternative tools, but the mode-level guidance is clear and sufficient for selection.

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