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

With no annotations, the description carries the full burden, and it does disclose the critical trait that deletion is permanent. It omits other behavioral context such as permission requirements, whether the call is idempotent, or what happens to existing check history; the schema's confirm field repeats the irreversibility note rather than extending it.

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 tight sentence with the destructive nature and the required identifier front-loaded. Zero wasted words.

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?

For a two-parameter destructive tool with no annotations and no output schema, the description covers permanence and id sourcing but leaves the confirm=true requirement entirely to the schema and says nothing about authorization or side effects. Adequate but with clear gaps.

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 only 50%, and watch_id has no schema description, so the description compensates by explaining the id's source (list_watches). The confirm parameter is well documented in the schema itself, so the description need not repeat it. It adds meaningful 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?

The description names a specific verb (permanently stops/delete) and resource (watch), plus the identifying key (watch_id). It points to list_watches for discovery, which lightly separates it from the sibling read tool, though it does not explicitly contrast with create_watch. Clear but not maximally differentiated.

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 parenthetical '(see list_watches)' tells the agent how to obtain the required watch_id, which is useful procedural guidance. However, there is no statement of when this tool is appropriate versus alternatives or any prerequisites beyond the id lookup.

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