pilot_app

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

Goes well past the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) by disclosing the desktop-app and licence prerequisites, that the command replaces any pending command, that field application order is open/screen/chart/run, that the user sees each step in the status bar and journal, and that the response always carries pilot_enabled. These are exactly the operational facts an agent needs and none are in the schema.

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 blocking prerequisite before any capability detail, which is the right priority, and each later sentence adds a distinct fact (ordering, when-to-use, caveats, response field). It is slightly long and the install/licence material could be tightened, but no sentence is pure 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?

For an 8-parameter, zero-required, no-output-schema tool that acts on a GUI, the description covers prerequisites, licensing, mutual exclusions, effect ordering, user-visible feedback, and the pilot_enabled response field. Nothing needed to invoke it correctly 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 per-parameter meaning is already carried by the schema, but the description adds cross-parameter semantics the schema cannot: fields combine in one call and apply in a fixed order, and a call replaces any pending command. It restates the run/prompt exclusion rather than adding to it, which keeps it just below a 5.

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 capability set with concrete verbs and objects (open a .stly document, switch screen, show a chart, start a backtest, display a note, send a prompt) and names the sibling it is not (backtest_graph). An agent can distinguish this from backtest_graph or compose_graph without opening either schema.

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 an explicit selection rule: use this when the user should watch the work in the app, otherwise use backtest_graph to get numbers back directly. It also states the hard preconditions (app open, piloting enabled and off by default, Atelier or Portfolio licence) so the agent can decide not to call it at all.

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