Server Quality Checklist

Tool Scores

• publish_draftC
  2.9/5.0
  Behavior1/5

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

  There are no annotations, and the description only states the action without disclosing side effects, reversibility, or required permissions. For a state-changing operation, this is a significant gap.

  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 a single sentence, making it very concise. However, the '(Freepublish)' parenthetical adds potentially confusing jargon without clear benefit.

  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 single-parameter tool, the description covers the basic mechanism, but it lacks any context about consequences of publishing, expected outcomes, or error conditions. With no output schema and no annotations, the description is not fully complete.

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

  Parameters3/5

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

  The input schema already provides a description for media_id ('Draft Media ID'), and the description repeats this by saying 'by its Media ID.' With 100% schema coverage, the description adds no additional semantic value, 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 action ('Publish a draft') and the method ('by its Media ID'), distinguishing it from sibling tools like create_draft and delete_draft. The parenthetical '(Freepublish)' is ambiguous but does not obscure the core purpose.

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

  Usage Guidelines2/5

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

  No guidance is provided on when to use publish_draft versus the sibling tools. It does not mention prerequisites (e.g., draft must exist) or situations where publishing would be inappropriate.

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

• delete_draftB
  3.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description alone must disclose behavioral traits. It only states the action (delete) without mentioning permanence, permission requirements, or consequences, leaving critical transparency gaps for a destructive 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 single-sentence description is extremely concise, front-loaded, and contains no filler or repetition, earning a top conciseness score.

  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?

  While the tool is simple and the parameter is fully documented, the description lacks essential context such as whether deletion is permanent or irreversible. Given that this is a mutation tool with no annotations, the description should provide more behavioral context to be complete.

  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 with 'Draft Media ID to delete,' and the description adds no further parameter meaning, matching the baseline for full schema 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 uses a specific verb 'Delete' and identifies the resource as 'a draft from the Draft Box,' clearly distinguishing it from sibling tools like create_draft, publish_draft, and image uploads.

  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 intended use is implied by the description—use when you need to delete a draft—but there is no explicit guidance on when not to use it or alternatives compared to sibling tools.

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

• upload_article_imageA
  3.8/5.0
  Behavior3/5

  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 that the tool returns a URL, which is important for invoking it, but does not mention potential file restrictions, overwrite behavior, or authentication requirements. For a simple upload, 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?

  A single, front-loaded sentence delivers the essential information (action, context, return value) without unnecessary words. Every word earns its place.

  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 one-parameter upload tool with no output schema, the description sufficiently covers purpose and expected result. It does not detail file format limits or edge cases, but the simplicity of the tool and clear schema make this adequate for an agent to select and invoke it 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 input schema provides 100% coverage of the single parameter (filePath) with a clear description ('Absolute path to the image file'). The tool description adds no additional parameter-level semantics, 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 a specific action ('Upload'), resource ('an image'), and context ('for use INSIDE article content'), plus the return value ('returns URL'). This distinguishes it from the sibling upload_cover_image by emphasizing 'inside' content.

  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 phrase 'INSIDE article content' implies this tool is for inline images rather than cover images, but it does not explicitly name alternatives or state when not to use it. The guidance is implied, not directly stated.

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

• upload_cover_imageA
  3.8/5.0
  Behavior2/5

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

  No annotations are provided, and the description only states return value (media_id). It does not disclose side effects, authentication requirements, file constraints, or whether this replaces an existing cover. For a mutation tool, this is insufficient behavioral 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?

  Single sentence, front-loaded with verb and purpose, no redundant 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 single-parameter upload with return value specified, the description is mostly complete, but lacks any note on integration with draft creation or image validation limits.

  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?

  Input schema has 100% coverage for the single filePath parameter, so the description adds no extra meaning. 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?

  Description uses specific verb 'Upload' + resource 'image' with clear purpose 'article COVER/THUMBNAIL', and distinguishes from sibling upload_article_image by specifying the use case.

  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 the specific use case (cover/thumbnail) which implicitly guides selection, but does not explicitly mention when not to use or alternative tools.

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

• create_draftA
  3.9/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden of disclosing behavior. It does mention that the draft is saved to Draft Box, but it omits important details such as requirements for thumb_media_id (e.g., being previously uploaded via upload_cover_image) and what the response contains. The disclosure is minimal but not misleading.

  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 one concise sentence that is front-loaded with the key action and context. Every word contributes value, with no repetition or filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool lacks an output schema and the description does not explain return values or the draft's role in the broader workflow (e.g., that it can later be published via publish_draft). The description is adequate for a basic create operation but leaves out useful contextual connections to sibling tools.

  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 coverage is 100% with all six parameters described in the input schema. The description adds no additional parameter-level meaning, so the baseline of 3 applies. It does not clarify relationships between parameters (e.g., thumb_media_id must be from a cover upload), but the schema already defines each parameter's role.

  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 specifies the action ('Create'), the resource ('a new article draft'), and the context ('saves to Draft Box'). This distinguishes it from sibling tools like publish_draft and delete_draft, making its purpose 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 phrase 'saves to Draft Box' implies the tool is for creating drafts, not publishing, which gives clear usage context. However, it does not explicitly state when not to use it or mention alternatives like publish_draft, though sibling names provide inferable guidance.

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