Write SSH File

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

Beyond the readOnly/idempotent/destructive hints, it discloses that prod is blocked by policy and that the result never contains file content, only path/mode/byte counts and command status. This is valuable behavioral context not present in annotations.

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

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

Three concise sentences: action, policy, and output shape. Each sentence earns its place with no tautology or filler.

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

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

The policy and output coverage are good, but the high parameter count and ambiguous confirmationText/confirmation_text fields are not addressed. The output schema reduces the need to document return values, yet the description still leaves a real gap in correct invocation.

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

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

Schema description coverage is 0% for 9 parameters, and the description does not compensate. It does not explain content format, confirmation flow, confirmationText vs confirmation_text, timeoutMs, workspaceId, or connectionId; 'writes or appends' only loosely maps to the mode enum.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

First sentence states a specific verb+resource ('Writes or appends a remote file through SSH') and the description adds mode and environment scope. This clearly distinguishes the tool from read/list/exec siblings and, by contrast with patch_file, indicates full-file write/appending behavior.

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

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

Gives explicit environment-based usage policy: dev allows ordinary paths, test/high-risk paths require confirmation, prod is blocked by policy. It omits a named alternative such as patch_file, so it misses the explicit 'use X instead' bar for a 5.

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