Live Keys Page

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

With no annotations, the description carries the full burden and does most of it: it discloses that the input appears as 'screen keys' (so live_midi/live_played must be patched to it), that the reply contains addresses on this computer and the phone, that phone=True mounts a panel requiring a sender name, and crucially that the audio comes from the computer's speakers rather than the phone stream and that opening the keys stops the phone stream. It does not say how the page is closed/torn down or what preconditions exist (engine running, phone server up).

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?

Purpose and the key warning are reasonably front-loaded, but the description is long and dense with run-on sentences that mix selection guidance, UI feature inventory (octaves, sustain, velocity, Z/Q rows, arrows, Space), and side-effect warnings. Much of the keyboard feature list helps the agent brief the person, but several clauses overlap and could be tightened.

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?

An output schema exists, so return values need not be fully described, yet the description still usefully says the reply carries the computer address and the phone's. Side effects (stream stops, audio from computer speakers) and the coordination step ('Tell the person before their keys first sound') are covered. Missing only lifecycle details: how to close the page and required preconditions.

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 0%, so the description must supply meaning and it largely does: 'phone=True also puts a panel on the phone page with a button that opens the keys' and 'sender: your name, as phone_panel_show takes it' give both optional parameters purpose and format. The required 'project' parameter is only implied ('this project's running engine') and never explicitly explained.

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 specifically what the tool provides: an on-screen keyboard that plays into the project's running engine as the input 'screen keys', with no virtual MIDI port. It explicitly distinguishes itself from the real-instrument path (midi_sources, live_midi). The only weakness is that the action verb (serve/open a page) is implied by 'The reply gives the address on this computer (the engine serves it)' rather than stated up front.

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?

Opens with 'Optional:' and gives the exact when-to-use condition (someone with no MIDI instrument who wants to play a part). It also gives an explicit when-not: 'A real keyboard needs none of this (midi_sources, live_midi).' The phone=True path and its purpose are spelled out, so an agent can choose correctly without opening any schema.

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