Delete Attachment

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, but the description adds crucial behavioral context: 'This cannot be undone' and the two-step confirmation process. It also reveals that a preview is returned on the first call, which is non-obvious and valuable for the agent to know. This goes beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences: clear purpose, safety warning, and usage detail. It is front-loaded with the action, then states irreversibility, then explains the confirmation flow. No words are wasted; each sentence serves a distinct purpose.

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

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

The description covers the deletion, irreversibility, and confirmation mechanism, which are essential. However, it leaves gaps: it does not explain the required resource parameter, and the 'preview returned by the first call' is vague without an output schema. These omissions prevent it from being fully complete for a 3-parameter tool.

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

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

The schema covers id and confirm well, but the resource parameter (required, enum) has no description in the schema, and the tool description does not clarify it. The description mentions 'by id' but omits the need to specify the parent resource type (epic, user_story, task, issue, wiki_page). This is a significant semantic gap, especially since resource is required, so the agent might not know to include it.

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

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

The description starts with 'Delete an attachment by id,' which is a specific verb+resource statement that clearly identifies the tool's function. It distinguishes itself from sibling tools like attachment_upload, attachment_list, and attachment_download by focusing on deletion, and from other delete tools by specifying attachment.

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

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

The description explains the confirmation protocol: 'elicitation-capable clients are prompted interactively; others must call again with confirm: true after reviewing the preview returned by the first call.' This gives clear operational usage guidance. However, it does not explicitly mention when to use this tool versus alternatives (e.g., if you need to remove a parent resource, use that resource's delete tool), so it falls 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.