Skip to main content
Glama

aw.input.begin

Reserve bounded encrypted staging for one explicitly selected file. NO source publication or job retirement until validated commit;2 pending/max24 identities.

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": {
      "session": "<session>",
      "inputId": "<inputId>",
      "format": "<format>",
      "totalBytes": "<totalBytes>",
      "sha256": "<sha256>",
      "selectedByUser": "<selectedByUser>"
    },
    "name": "aw.input.begin"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatYes
sha256Yes
inputIdYes
sessionYesPrivate short-lived session capability returned by aw.session.open. Never publish or log it.
totalBytesYes
selectedByUserYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Goes beyond annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false) by disclosing that staging is encrypted and bounded, that nothing is published or retired before a validated commit, and that only 2 pending identities are allowed out of a max of 24. That is real operational context absent from the structured fields, though the cryptic "2 pending/max 24 identities" phrasing leaves the limit's exact semantics unclear.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the action and followed by the safety guarantee, so there is little waste. The trailing "2 pending/max 24 identities" is terse to the point of ambiguity and reads like an internal note.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 6-parameter, all-required staging mutation with no output schema and low schema coverage, the description omits what a successful call returns (staging handle, expiry) and how the reservation interacts with write_chunk/commit/abort. The session capability's sensitivity is only documented in the schema, not the description.

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 only 17% schema coverage and 6 required parameters, the description must carry weight: "bounded" explains totalBytes' 4 MiB cap, "one explicitly selected file" explains selectedByUser const true, and "encrypted staging" frames the sha256/format pair. Still silent on inputId's UUID role and the session capability beyond what the schema pattern already says.

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 a concrete verb and resource: "Reserve bounded encrypted staging for one explicitly selected file." It clearly distinguishes staging from publication/commit, though it never names the sibling tools (aw.input.write_chunk, aw.input.commit) that continue the workflow.

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?

Implies this is the first step of a staging workflow and that commit must precede publication ("NO source publication or job retirement until validated commit"), which orients the agent. It never explicitly says when to use this versus aw.input.write_chunk or what prerequisite (aw.session.open) must be satisfied.

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