DebugDeleteWatchpoint

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

No annotations are supplied, so the description carries the full burden. It does add genuine context ('Runs outside batch mode') and a classification tag, but the '[read-only]' tag sits in tension with the destructive verb 'Removes' and is never reconciled, and nothing is said about idempotency, error behavior for a nonexistent watchpoint_id, or whether state_handle must come from a live debug session.

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?

Two bracketed tags plus a single short sentence, with the identifying verb front-loaded and the batch-mode caveat second. Efficient, though the '[read-only]' tag is arguably noise given the mutation it describes.

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 three parameters, no output schema, and no annotations, the description should do more: it says nothing about the return value (even a note on whether the deleted watchpoint is echoed back), nor about failure modes for an invalid id or expired state_handle. It is minimally viable but leaves real gaps for a stateful debugger mutation.

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 100%, including a documented enum for 'detail' and an explanation of the opaque 'state_handle'. The description adds nothing beyond the schema, so the 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?

Names a specific verb and resource ('Removes a watchpoint'), and the resource noun itself separates it from the breakpoint siblings (DebugDeleteBreakpoint) and from DebugCreateWatchpoint / DebugListWatchpoints. It stops short of explicitly routing against those siblings, but an agent can identify the operation without opening the 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?

'Runs outside batch mode' is a real usage constraint that tells the agent not to call this inside a DebugBatchBegin/BatchEnd session. However, there is no explicit when-to-use clause, no statement that a watchpoint must first exist (via DebugCreateWatchpoint), and no guidance on what to do with an unknown or stale watchpoint_id.

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