DebugCreateWatchpoint

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

With no annotations, the description carries the burden and does disclose the key traits: it requires a stopped debuggee, is unavailable in batch mode, and has a stop-on-change effect with conditional gating. It omits whether the watchpoint persists after continuing and that it must later be removed via the delete tool, leaving lifecycle behavior implicit.

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?

A single dense sentence with the effect and the batch-mode caveat front-loaded; nothing is wasted. The leading [read-only] [debug] tags add mild noise, and the read-only tag sits oddly on a tool that creates debugger state.

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?

Prerequisites and mode restriction are covered, which matters for a 4-parameter mutation of debugger state with no output schema. However, the description never says what a successful call yields (presumably a watchpoint identifier needed by DebugDeleteWatchpoint) or how it relates to the list/delete watchpoint tools.

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 all four parameters including the detail enum and the state_handle are already documented. The description only restates the variable and optional condition, adding no syntax, path, or scope guidance beyond the schema — baseline 3 applies.

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 concrete verb and resource — it watches a variable of the stopped debuggee — and explains the observable effect (stops when the variable changes, optionally under a condition). It is clearly distinguishable from DebugListWatchpoints/DebugDeleteWatchpoint by what it does, though it never names those siblings explicitly.

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 a clear precondition (a stopped debuggee) and an explicit exclusion ("runs outside batch mode"), which tells the agent when this tool is applicable and when it is not. No alternative tool is named (e.g. list/delete watchpoints, or stepping for fine-grained control), so it falls short of the 5 bar.

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