Citiview Agent Market

storage

storage

Read-only

File storage for agents on R2 with share links. Upload (base64, text or copy from a URL, up to 95 MB; up to 5 GB with upload_large), renew, get, list or delete. Priced by size and time: $0.002 per started 10 MB per week (above 100 MB $0.05 per GB-week); scratch files kept 1-24 hours from $0.002. Downloads are free. Files are private to the paying wallet. Costs $0.01 USDC per call (x402).

Input Schema

Name	Required	Description
`id`	No	For renew/get/delete
`url`	No	Copy a file from this URL (set max_mb)
`name`	No
`text`	No
`action`	No	put (default), upload_large, renew, get, list, delete
`max_mb`	No
`size_mb`	No	Total size for upload_large or renew
`content_type`	No
`expires_days`	No	1-365, default 7
`expires_hours`	No	1-24: scratch tier
`content_base64`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 14, 2026

changedInput schema / properties / action / description

Previous value: -"put (default), get, list, delete"New value: +"put (default), upload_large, renew, get, list, delete"

changedInput schema / properties / expires_days / description
```
Previous value: -"1-30"New value: +"1-365, default 7"
```

addedInput schema / properties / expires_hours

Added value: +{
+  "description": "1-24: scratch tier",
+  "type": "integer"
+}

changedInput schema / properties / id / description

Previous value: -"For get/delete"New value: +"For renew/get/delete"

addedInput schema / properties / max_mb
```
Added value: +{
+  "type": "number"
+}
```

addedInput schema / properties / size_mb

Added value: +{
+  "description": "Total size for upload_large or renew",
+  "type": "number"
+}

changedInput schema / properties / url / description

Previous value: -"Copy a file from this URL"New value: +"Copy a file from this URL (set max_mb)"

AddedOct 14, 2026

TDQS

B3.2/5.0

Behavior1/5

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

The annotations declare readOnlyHint=true, but the description explicitly advertises state-changing operations ('Upload ... renew ... or delete'). Uploading and deleting files are writes, so the safety annotation is contradicted and an agent trusting readOnlyHint would wrongly treat this as a non-mutating read. Flagged as an annotation contradiction.

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?

Front-loaded with purpose and the action set, then pricing and limits; nearly every sentence carries operative information. The pricing clauses are dense but not redundant, and the description stays within a compact paragraph.

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 an 11-parameter, multi-action tool with no output schema, the description covers actions, size limits, retention tiers, privacy scope, and per-call cost, which is close to what an agent needs. Return-shape details are absent but arguably out of scope given no output schema.

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?

With 55% schema coverage across 11 params, the description meaningfully compensates: it explains the base64/text/URL source options, the 95 MB vs 5 GB tier tied to upload_large/max_mb, and the scratch tier's 1-24 hour retention tied to expires_hours. It adds real meaning beyond the schema, though a few fields (name, content_type, expires_days) remain unelaborated.

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

Purpose4/5

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

States specific verbs (upload, renew, get, list, delete) and a specific resource (file storage on R2 with share links), so an agent knows exactly what capability this is. It stops short of 5 because it never names or distinguishes itself from the sibling 'files' tool, which an agent could plausibly confuse it with.

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?

Usage is implied through the action list and the size tiers ('up to 95 MB; up to 5 GB with upload_large'), which helps pick the right upload mode. However, there is no explicit when-to-use/when-not guidance and no routing to or away from alternatives such as 'files' or 'docs', leaving the agent to infer selection.

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

All Citiview Agent Market tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?