Skip to main content
Glama

Upload reusable JSON

upload_json

Store one JSON document in private temporary storage for repeated process_json queries; this does not run a jq filter. Use when the same input will be queried more than once. For a single query, pass input or url directly to process_json instead. Provide exactly one of input or url, never both. A local file must be sent to REST POST /uploads by the client; this tool cannot read local paths. Maximum 5 MiB; URLs must be public HTTPS JSON on port 443, without credentials, private addresses, or custom headers. URL fetching is bounded to three redirects and ten seconds. Returns success:true, a secret upload_id, expires_at (UTC), and size_bytes. The ID is reusable for 15 minutes; uploads do not refresh expiration when queried. Uploads are immutable: create a new upload to change the JSON, then delete the old ID. Anyone holding the ID can inspect, query, or delete it. Use get_upload for metadata, process_json for contents or filtering, and delete_upload for early cleanup. Consumes one shared daily quota call on the free tier; active prepaid passes bypass that counter. Retrying creates another upload. No signup; a UUID bearer header selects the access tier but does not establish upload ownership. Failures return success:false and error, with status 400 for invalid input/URL/JSON, 413 for oversize data, 415 for unsupported content, 502/504 for URL failures, or 503 for storage failure. Exhausted quota returns a tool error with remaining:0, reset_at, and a structured upgrade offer linking pricing and checkout; inspect _meta.rateLimit for limit and reset.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "upload_json"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoPublic HTTPS JSON URL to fetch once and store, up to 5 MiB. Port 443 only; no credentials, private networks, or custom headers. Choose url or input, never both.
inputNoOne JSON value to store, including null. Choose input or url, never both. Local files must first be uploaded through POST /uploads.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

Well beyond the annotations: 15-minute TTL, no refresh on query, immutability, retry creating a duplicate upload, secret ID with anyone-holding-it access, quota consumption on the free tier, and a full error-code table. Annotation consistency is sound (non-idempotent matches "retrying creates another upload"). The only shortfall is that fetch-time behavior for the stored document's size/content validation beyond the listed status codes is compressed.

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 sibling contrast, then constraints, then return shape, then errors — a sensible ordering. It is dense, however: quota, bearer auth, and upgrade-offer details consume sentences that a first-time caller must parse before reaching the simple "one of input or url" rule.

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 two-parameter write tool with no output schema, the description covers return fields (upload_id, expires_at, size_bytes), lifecycle limits, immutability, access semantics, and failure modes. Nothing an agent needs in order to call it correctly or interpret the response is missing.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline applies. The description does add real value by stating "Provide exactly one of input or url, never both" — an XOR constraint the schema does not encode — and clarifying that local paths are not readable. That is genuine added meaning, but it repeats the per-parameter exclusivity already noted in the schema field descriptions.

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?

Opens with a specific verb and resource ("Store one JSON document in private temporary storage") and immediately bounds the purpose for "repeated process_json queries; this does not run a jq filter." That negative clause cleanly separates it from the sibling that does filtering, so an agent can pick between them without opening either schema.

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?

Gives an explicit when-to-use rule ("Use when the same input will be queried more than once") and an explicit when-not rule with the alternative ("For a single query, pass input or url directly to process_json instead"). It further routes to get_upload, delete_upload, and process_json by role, leaving no sibling ambiguity.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources