createCaseAttachmentUploadUrlIssue a signed URL for uploading a file to a case. The client must PUT the bytes to the returned URL with the returned Content-Type, then call the finalize endpoint so the attachment becomes visible on the case.
| Name | Required | Description | Default |
|---|---|---|---|
| case_id | Yes | The case's unique identifier | |
| filename | Yes | ||
| queue_id | Yes | The queue's unique identifier | |
| mime_type | Yes | ||
| size_bytes | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes meaningfully beyond the sparse annotations (all false hints) by disclosing that the tool issues a signed URL and that the attachment does not become visible until the finalize endpoint is called — a genuinely non-obvious two-phase behavioral trait. It also specifies the PUT-with-Content-Type requirement, which an agent could not infer from the schema. Signed-URL expiry and authorization needs are not mentioned, but the core behavioral disclosure is strong.
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, roughly 50 words, with the core purpose front-loaded in the first sentence and the essential follow-up protocol in the second. Every clause earns its place; there is no filler or restatement of the title.
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?
For a moderate-complexity tool with no output schema and minimal annotations, the description conveys the critical facts: what is returned (signed URL and Content-Type), the exact PUT protocol, and the dependency on the finalize endpoint. Minor omissions — signed-URL expiry, explicit size-limit emphasis, and failure behavior — leave some room, but the core flow is fully actionable.
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 only 40% (case_id and queue_id), so the description must partially compensate for filename, mime_type, and size_bytes. It adds real meaning by tying mime_type to the 'returned Content-Type' and framing the file fields as the payload to PUT, but it does not individually explain their constraints or semantics, leaving the 50MB size ceiling and length limits solely to the schema.
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?
States a specific verb and resource — 'Issue a signed URL for uploading a file to a case' — which is unambiguous and anchored to the case domain, distinguishing it from generic upload-URL siblings like createFileUploadUrl. The finalize-step mention further scopes its role. It does not explicitly name a sibling for disambiguation, but the case-specific framing is sufficient.
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?
Provides explicit protocol guidance: the client 'must PUT the bytes to the returned URL with the returned Content-Type, then call the finalize endpoint,' which tells an agent exactly how to consume the result and that a mandatory follow-up call exists. It does not state exclusions or route among alternatives such as createFileUploadUrl, but the intended usage context is clearly conveyed.
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.