Server Quality Checklist

Tool Scores

• delete_uploadA
  4.5/5.0
  Behavior4/5

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

  The description goes beyond the destructiveHint annotation by stating the deletion is irreversible, the file and its links stop working immediately, and errors such as not found, already deleted, or wrong owner surface as normal tool errors. This gives an agent useful behavioral expectations.

  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 sentences with the main action and consequence front-loaded. Every sentence contributes: what it does, how to get the id, and what error behavior to expect. There is no filler.

  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 one-parameter destructive tool with output schema and annotations, this description is complete. It covers purpose, side effects, id provenance, and error behavior. An agent has everything needed 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.

  Parameters4/5

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

  The schema already documents `id` at 100% coverage, and the description adds retrieval guidance: use the response from upload_image right after uploading, or list_uploads if the id is no longer available. This is genuinely useful beyond the schema's parameter description.

  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 action and resource: 'Permanently delete one of your YourImageShare uploads by `id`'. It clearly distinguishes itself from siblings by present itself as the deletion tool while upload_image/list_uploads are framed as id sources.

  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 gives clear usage context: use when you intend a permanent deletion, and it explains how to obtain the id from upload_image or list_uploads. It doesn't explicitly state when not to use, but since the siblings are upload/list tools, there is no deletion alternative needing exclusion.

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

• upload_imageA
  4.8/5.0
  Behavior5/5

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

  Beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description discloses important behavior: it creates an upload, returns three distinct URL types, supports optional auto-deletion via expiresIn, and returns errors as normal tool errors rather than exceptions. This gives the agent a clear behavioral model without contradicting the 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 dense but every sentence contributes: accepted types, size limits, input modes, mutual exclusivity, return URL purposes, and error behavior. It is front-loaded with the core purpose and then details the constraints. No filler or redundant restating of the title.

  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 tool with 4 optional-looking parameters, practical constraints, an output schema, and no explicit required fields, the description fully compensates. It clarifies the real requirement (either path or base64+filename), describes what the agent can expect as output, and covers failure modes. The agent can invoke this tool correctly with minimal additional inference.

  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?

  Although schema description coverage is 100%, the description adds critical semantic constraints not visible in the schema: path and base64+filename are mutually exclusive, filename is required with base64 but inferred from path, and expiresIn controls auto-deletion. It also explains what the return URLs mean, adding value beyond the raw parameter definitions.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb and resource: 'Upload an image or video to YourImageShare and get back a shareable link.' It clearly distinguishes this tool from its siblings list_uploads and delete_upload by focusing on the creation/upload action rather than listing or deleting.

  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 gives clear context for when to use this tool: uploading images/videos, with accepted formats and size range. It also explains the two input modes (path vs base64+filename) and when each is appropriate, including the 'never both' rule. It doesn't explicitly name sibling alternatives for when-not-to-use, but the upload vs list/delete distinction is obvious.

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

• list_uploadsA
  4.9/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds genuinely useful behavioral traits beyond those: pagination behavior ('50 per page'), the out-of-range page behavior ('returns an empty `data` array, not an error'), and the exact composition of results ('same three link fields `upload_image` returns, plus `title` and `created_at`'). These are not derivable from annotations or schema.

  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 sentences, each earning its place: purpose+scoping, result-shape, and edge-case behavior. Core purpose is front-loaded in the first sentence. No filler, no repetition of schema or annotation content.

  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 single-optional-parameter read-only tool with an output schema and safety annotations, the description covers everything an agent needs to invoke it correctly: what it returns, how pagination works, when to prefer it, and how errors manifest. The output schema handles return structure, so nothing material is missing.

  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% (the `page` parameter is already documented with type, minimum, and default), so the baseline is 3. The description adds value by explaining what page means in operation: pages are 50 items each, and an out-of-range page yields an empty array rather than an error. This enriches the schema's bare parameter definition without contradicting it.

  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+resource ('List your YourImageShare uploads') and adds concrete scoping details: 'newest first, 50 per page'. It also differentiates from siblings by tying the tool to finding an upload's `id` for `delete_upload`, and by contrast with `upload_image`. An agent can distinguish this from both siblings without opening their schemas.

  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 this to find an upload's `id` (needed by `delete_upload`) when you only have its URL or remember it by content'. It also states the limiting constraint that should trigger this tool: 'there's no lookup-by-URL endpoint'. This is exactly the kind of routing information an agent needs.

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