Skip to main content
Glama

aw.input.write_chunk

Append one exact canonical-base6432768-byte chunk (last=remainder) to this attempt in order. Exact retries reconcile; binary bodies may reach client/model history.

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>",
      "attempt": "<attempt>",
      "offset": "<offset>",
      "data": "<data>"
    },
    "name": "aw.input.write_chunk"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataYes
offsetYes
attemptYes
inputIdYes
sessionYesPrivate short-lived session capability returned by aw.session.open. Never publish or log it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare the write nature (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the description's main added value is that exact retries reconcile (idempotency) and that binary bodies may reach client/model history — a useful privacy disclosure. It does not cover what happens on out-of-order or duplicate-offset writes, or what commit does with the accumulated chunks, so the behavioral picture remains partial.

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?

Two dense sentences with no filler, front-loading the operation and following with retry and privacy notes. The compression goes too far in places, producing a run-together token that has to be re-parsed to recover 'canonical base64, 32768-byte chunk'.

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

Completeness3/5

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

For a stateful, sequenced write tool with five required parameters and no output schema, the description covers the mechanics of a single call but not its place in the protocol. An agent still has to infer session/attempt lifecycle, ordering guarantees on failure, and how completion is signalled.

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 only 20% — just the session capability — so the description must carry the rest, and it partially does: it implies data is a canonical-encoded 32768-byte chunk with a smaller final remainder, and that offset advances in order. It never explains the attempt or inputId identifiers, nor the maximum total size bound, so half the parameters are still unexplained in prose.

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?

The description states a specific verb and resource — appending one chunk of data to a named attempt — so an agent can tell this apart from commit/status/abort siblings in the same family. It never names those siblings and the encoding phrase is mangled ("canonical-base6432768-byte"), so the operation is clear but the differentiation is left implicit.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance, and no statement of prerequisites such as opening a session or beginning an attempt before appending. The only usage signal is "in order" and "last=remainder", which imply a sequential multi-call flow without saying so, and no alternative (e.g. commit) is ever named.

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