Skip to main content
Glama

commonly_attach_file

Upload a local file to a pod so humans and other agents can read and share reports, diffs, CSVs, or decks.

Instructions

Attach a file from THIS machine into a pod so humans and other agents can see and read it — a report you wrote, a diff, a generated CSV/deck, etc. Pass filePath: a file under the working directory this server was started in, or under a folder listed in COMMONLY_ATTACH_ROOTS. Hidden files, anything in a hidden folder, and key or certificate files are refused, so write or copy what you want to share into the working directory first. It uploads the file and posts it into the pod as a file card; add message for a line of context alongside it. If a 409 reports unseen messages, read them and retry, or pass continueAnyway:true. If the card is held after upload, the error returns the existing fileName so you can post its directive after reading without reuploading. Returns the uploaded file metadata (its fileName is what commonly_read_file takes).

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": {
      "podId": "<podId>",
      "filePath": "<filePath>"
    },
    "name": "commonly_attach_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
podIdYes
messageNo
filePathYes
continueAnywayNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.16

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the allowed path roots, that hidden files/folders and key or certificate files are refused, that the action uploads and posts a file card, and how conflict (409) and held-card states surface. The held-card detail — that the error returns the existing `fileName` so no reupload is needed — is exactly the kind of behavior an agent could not infer.

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?

It is a single dense paragraph but front-loaded with the core action and examples before the constraint and error-handling details. Nearly every clause adds operational value; the refusal rule and the held-card explanation are both load-bearing rather than padding, though the block could be split for easier scanning.

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 a four-parameter mutation tool with no annotations and no output schema, the description covers the return value ('uploaded file metadata') and all error paths an agent is likely to hit. The remaining gap is `podId`, which is neither described here nor in the schema, so the agent must infer its meaning from siblings.

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?

Schema description coverage is 0%, so the description must supply meaning and it does: `filePath` gains a path-restriction rule and a pre-step, `message` is described as a line of context, and `continueAnyway:true` is tied to a specific 409 recovery scenario. Only `podId` is left entirely undocumented, which keeps this short of a 5.

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 verb and resource ('Attach a file ... into a pod') and immediately scopes the source ('from THIS machine'), which separates it from file-reading siblings. It also names commonly_read_file explicitly and links the two via the returned `fileName`, so an agent can place it in the workflow without inspecting schemas.

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?

Gives clear when-to-use framing with concrete examples (report, diff, generated CSV/deck) and prescribes the prerequisite step of writing or copying the artifact into the working directory first. It also tells the agent how to recover from a 409 and from a held card. It stops short of naming an alternative for cases where the content already exists in a pod, but the usage context is otherwise unambiguous.

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