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

Annotations only tell the agent this is a non-read-only, non-destructive, non-open-world call. The description goes much further: it discloses that the engine force-overwrites parts of package.json (dev/build/typecheck scripts and vendored command-frame + mock packages), that baseline/build deps are re-added only when undeclared so user pins survive, and that it shares a rate bucket with start_preview. This is exactly the mutation-side detail annotations cannot 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 core action and its payoff (the build gate result) are front-loaded, and every subsequent sentence adds non-redundant behavior (forced package.json fields, dep re-add rules, rate bucket). It is dense and slightly long, but no sentence is 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?

With no output schema, the description still explains the return value ('Returns the gate result'), covers the mutation side effects, the running/cold precondition, and the rate-limit interaction with a sibling. Nothing an agent needs to call this 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?

There is a single parameter (flowId) with 0% schema description coverage, and the description never mentions it or its format. It is self-evident from the name and required, so the gap is mild rather than disqualifying, but the description adds no semantic value over the bare schema.

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 (reconcile/sync) and resource (preview sandbox vs. the flow's current files), plus the concrete downstream action (run the green-build gate: tsc + vite build). An agent can distinguish this from flow_start_preview, flow_get_preview_status and flow_write_flow_files without opening any 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 real usage context — 'the fastest way to know your code actually compiles' — and names the sibling it shares a rate bucket with (start_preview), with the explicit instruction 'sync once per change-set, not per file.' It stops short of a full when-to-use/when-not matrix against every preview sibling, but the routing guidance is clear.

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