crosspad_flash

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

The description discloses far beyond the annotations: a preflight always runs and is always returned (refusal included), confirmation is mandatory before any write, board-revision mismatch is a hard blocker because the wrong image 'looks like dead hardware', and the port-role refusal is never overridable. It also reveals job semantics (wait_seconds=0 returns a task handle; a timeout is not an error) and wait_boot returning a BootResult, none of which the annotations convey.

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?

The description is dense but logically ordered: danger tier first, then preflight details, then ESP specifics, then STM specifics, then job semantics — with the safety-critical 'needs a confirmation before writing anything' front-loaded. It runs long, but with 15 parameters and two hardware targets every sentence earns its place; light structural breaks would make it exemplary.

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 the most complex and dangerous tool in the set (15 params, destructiveHint=true, no required params), the description covers the complete lifecycle: preflight, confirmation, per-target transports and methods, blocker override semantics, async job polling, and boot verification. The presence of an output schema means return values need no further elaboration. Nothing an agent needs to safely invoke this tool 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 100%, so the baseline is 3. The description genuinely adds cross-parameter meaning: it ties force, dry_run, and confirm_token into the preflight/confirmation lifecycle, scopes delta_base to ESP OTA-only, and explains the wait_seconds-to-crosspad_task coupling. The preflight paragraph gives force and dry_run behavioral weight the schema alone cannot.

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?

Opens with '[ESP HW | STM HW] Flash firmware' — a specific verb and resource that names both hardware targets. The scope is unambiguous and the sibling tools (build, repo_status, devices, doctor, snapshot, toolsets, task) are clearly distinct: this is the only one that writes firmware.

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?

The description explains the full invocation lifecycle: a preflight always runs and returns a confirmation_required result, the identical call is re-issued with confirm_token to proceed, dry_run stops after preflight, and force overrides blockers. It also routes async polling to crosspad_task. What's absent is an explicit 'when not to use this tool' statement, though the siblings are different enough in purpose that this is a minor gap.

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