prepare_create_watch

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

Beyond the annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false), the description discloses that the return is a private browser-fragment draft, that no key or secret is embedded in the link, and that no notification is sent and no watch is created. These are material behavioral traits an agent cannot infer from the annotations alone.

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?

Three tight sentences with the critical 'DO NOT EXECUTE' warning front-loaded, followed by what the tool returns and what it does not do. No filler or repetition.

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 usefully characterizes the return value (private browser-fragment draft with no secret) and all non-effects. For a read-only, idempotent tool the safety and outcome picture is complete; only the parameter meanings are under-covered.

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 description coverage is 0% across 5 parameters, so the description carries the full explanatory burden, yet it only hints at asset_filter ('USDT/TRX') and address. Keywords like channel (webhook vs telegram), webhook_url, and direction are never explained, leaving most parameters semantically opaque.

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 precise verb+resource: 'Prepare (DO NOT EXECUTE) a TRON USDT/TRX watch creation' and specifies the artifact returned ('private browser-fragment draft'). This cleanly separates it from execute-style tools and from sibling 'prepare_delete_watch' by naming the exact action and asset scope.

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 clearly frames this as a preparation step whose output the owner reviews and confirms in the official console, and explicitly says it does not create a watch or send a notification. It does not, however, name alternatives such as validate_watch_config or explain when to prefer that tool over this one, so guidance is clear but not exhaustive.

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