Full system firmware upgrade

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

Annotations already flag destructiveHint=true, but the description goes well beyond them: immediate execution, multiple reboots, bricking risk if interrupted, and the fact that the MCP does not replicate the app's authenticated cloud package fetch. That last point is exactly the kind of behavioral constraint an agent cannot get from any structured field.

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?

Front-loaded with the operation and its danger, then the required inputs, then the confirmation rule. Nearly every clause carries new information; the trailing 'DESTRUCTIVE.' is mildly redundant given the brick warning and destructiveHint annotation.

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?

For a 5-parameter destructive mutation with no output schema, the description covers the essential risk profile, the calling prerequisite (user approval), and the surprising input requirement (agent-supplied base64 image). Device targeting rules live in the schema. Nothing critical for a correct call is missing.

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 coverage is 80%, so the baseline would be 3, but the description adds real meaning: it explains *why* firmwareBinaryB64 must be supplied (no cloud fetch, base64 .bin) and that confirm must follow explicit per-device approval. Those are motivations the schema descriptions only partially convey, though target/targetVersion handling in the description is thinner.

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?

States a specific verb and resource ('Run a full system firmware flash (SYSTEM_UPGRADE)') and names the underlying app routine (updateLoaderFirmwareMpy with shouldUpgradeFirmware=true), which pins down exactly which operation this is. It implicitly distinguishes itself from the partial/MPY flash siblings by insisting on the 'full system' scope, but never names flash_mpy or flash_check as the alternatives.

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?

It gives a clear precondition (explicit user approval before confirm=true) and explains why the binary must come from the caller rather than the app's cloud fetch. However, it never says when to prefer this over the closely named siblings flash_mpy, flash_check, or flash_config, leaving the agent to infer the boundary from the word 'full'.

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