deleteCaseAttachmentRemove a file from a case. The row is soft-deleted; deletion of the stored object is attempted best-effort.
| Name | Required | Description | Default |
|---|---|---|---|
| case_id | Yes | The case's unique identifier | |
| queue_id | Yes | The queue's unique identifier | |
| attachment_id | Yes | The attachment's unique identifier |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds meaningful nuance beyond those flags: the row is soft-deleted, and deletion of the stored object is attempted best-effort. This is valuable behavioral context — the agent learns the underlying file may survive the call, which affects downstream expectations (e.g., a subsequent download might still succeed). No contradiction with annotations; in fact, idempotentHint aligns well with soft-delete semantics.
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?
Two sentences with zero waste. The first sentence front-loads the core action, and the second delivers the critical behavioral qualifier (soft-delete, best-effort object deletion). Every phrase earns its place; nothing is redundant with the title or annotations.
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 essential behavioral nuance an agent needs for a destructive-but-soft operation: what gets removed (the row), what may survive (the stored object), and the best-effort nature. The only gap is the lack of return-value or error semantics, especially since no output schema exists, but for a simple three-parameter delete operation this is a minor omission and the idempotentHint annotation partially compensates.
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?
Schema description coverage is 100%, with all three parameters (queue_id, case_id, attachment_id) having brief but adequate descriptions of their role as unique identifiers. Per the rubric, the baseline is 3 when the schema does the heavy lifting, and the description adds no parameter-specific detail beyond what the schema provides. This is acceptable given the parameters are simple UUIDs with full schema documentation.
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 uses a specific verb ('Remove') and resource ('a file from a case'), clearly scoping the operation to case attachments. It implicitly distinguishes itself from sibling tools like deleteCase and deleteFile, though it doesn't name them explicitly. The clarity is good but not exceptional since it relies on the sibling names rather than explicit differentiation.
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 usage context is implied: this tool is invoked when a file attached to a case needs to be removed. However, there is no explicit guidance on when not to use it or which alternative to prefer, such as deleteFile for standalone files or getCaseAttachmentDownloadUrl for retrieving rather than deleting. The soft-delete note adds some selection-relevant behavior but doesn't fully route the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Despite detailed descriptions, many tool names are highly ambiguous, with multiple tools covering the same conceptual actions (e.g., acceptClarityCaptureSuggestion vs. acceptClarityTeamAssignmentSuggestion, or the many deleteClarity*Interview tools). The set is so large that distinguishing between, say, listClarityFolders, listClarityProcesses, and listClarityProcessSummaries requires reading deep into descriptions, reducing agent selection accuracy.
The naming convention is predominantly verb_noun (e.g., createClarityProcess, listAgents, deleteQueue), and is remarkably consistent across the 316 tools. There are only minor deviations, such as 'fileSuggestedClarityProcesses' (verb + adjective noun) and 'bulkUpdateCasePriority' (where 'bulk' could be seen as a prefix), but overall the pattern holds strongly.
With 316 tools, this server is extremely oversized for any single agent to manage effectively. The massive number of tools suggests poor modularization—many of these tools likely belong in separate, smaller servers focused on specific domains (e.g., Clarity, Pulse, Agent management). The cognitive load for an agent to choose from 316 options is very high, leading to frequent misselection.
The tool surface covers an extraordinarily wide range of operations across the Duvo platform: agents, runs, cases, queues, Clarity processes, skills, integrations, notifications, teams, and more. Most resource types have full CRUD and lifecycle management. Notable minor gaps exist (e.g., no tools for managing specific notification batch severities dynamically, and some interview management is missing batch operations), but for the platform's scope, coverage is impressively thorough.