Skip to main content
Glama
communitycad-mcp

communitycad-mcp

Official

Check a download

check_download
Read-only

Determines whether downloading a model or file will consume a daily download allowance and reports how many remain, without changing anything.

Instructions

Whether downloading this model would use one of the user's downloads, and how many are left. Changes nothing. The source of truth for counting: the first file of a model each UTC day uses one download; more files of that model the same day, repeats and the user's own models are free. Counted per network (IP) signed out, per account signed in (shared with the website).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "model_id": "<model_id>"
    },
    "name": "check_download"
  }
}

Input Schema

NameRequiredDescriptionDefault
file_idNoOptional: also check this file's daily cap.
model_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only supply readOnlyHint and openWorldHint; the description goes well beyond them by disclosing the exact quota accounting rules (first file per UTC day costs one, extra files/repeats/own models free) and the identity basis for counting (IP when signed out, account when signed in, shared with the website). That is the behavior an agent needs to interpret the result correctly.

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?

The answer and its no-side-effect nature are front-loaded, followed by the counting rules. The final sentence is dense and slightly hard to parse ('Counted per network (IP) signed out, per account signed in'), but no sentence is filler.

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?

With no output schema, the description does sketch the return ('whether... and how many are left'), and the quota rules make the result interpretable. Only the exact response shape and the meaning of model_id versus file_id remain implicit.

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 coverage is 50%: file_id already carries its own description, while model_id has none. The description implies model_id is the model whose quota is being checked and that per-file behavior matters, but it never states what file_id does beyond what the schema already says. Adequate, not compensating for the gap.

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?

States a specific check (would a download consume quota, and how many remain) against the model resource, and the phrase 'Changes nothing' cleanly separates it from the sibling download_file. An agent can tell instantly that this is a non-mutating pre-flight query rather than the actual download.

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

Usage Guidelines4/5

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

The 'Changes nothing' framing strongly implies this is a dry-run to call before download_file, and the counting rules tell the agent what the answer depends on. It stops short of explicitly naming download_file as the follow-up action or stating when not to bother calling it.

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