live_state

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but the description adds materially beyond them: the hard precondition that the desktop app must be installed, opened, and licensed (Atelier or Portfolio), and the guarantee that secrets are never exposed. Those are exactly the operational facts an agent needs before calling, and they are not derivable from the 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?

The blocking app/licence requirement is front-loaded in its own paragraph, then the content, then the usage hint and interpretation. Everything is on-topic, though the app-installation and licence requirements are restated in the opening and closing sentences, which costs a little density.

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?

With no output schema present, the description carries the return-value burden and does so: it lists the reported fields and defines both age_s and present. Combined with the precondition and licence constraints, an agent has everything needed to call this correctly or decide it cannot be called.

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?

The tool takes zero parameters, which sets a baseline of 4. The description still earns that baseline by documenting the shape of what comes back (age_s as seconds since the state file was written, present as false when the app has never written it), which is useful even though there is nothing to describe on the input side.

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-plus-resource (read the app's last reported state) and enumerates exactly what that state contains: workspace, chart, symbol, timeframe, indicators, graph nodes, current run, active assistant agent. It is clearly distinguished from the write-side sibling set_live_state, so an agent can separate the two 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 concrete usage triggers: 'check the effect of pilot_app or the context of the user's screen', plus an interpretation rule that a large age_s means the app is probably closed. It does not state an explicit when-not or name set_live_state as the write alternative, which keeps it short of a 5.

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