prepare_delete_watch

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

Adds substantial behavior beyond the annotations: it states this tool never issues DELETE (explaining why destructiveHint=false is safe), discloses downstream effects of the eventual deletion (notification/attempt history is removed, an in-flight delivery may still complete), and names the precondition (scoped GET, ownership, console confirmation).

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?

Four short sentences with the most safety-critical constraint front-loaded in parentheses. Zero filler; each sentence adds a distinct fact (stage, confirmation owner, side effects, non-execution).

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 one-parameter, non-executing staging tool with no output schema, the description covers the essential semantics. It leaves minor gaps: what artifact or handle the 'preparation' yields and whether it expires before the owner confirms.

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?

The single watch_id parameter has 0% schema description coverage, so the description must carry the load. It implies the ID must reference an *owned* watch fetched via a scoped GET, which is meaningful, but it never names or describes watch_id, its format, or how to obtain it.

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 (prepare, explicitly DO NOT EXECUTE), a specific resource (an owned watch), and the precondition (after a scoped GET). The parenthetical '(DO NOT EXECUTE)' disambiguates it from any real delete operation in a way an agent can act on immediately.

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?

Clearly positions the tool as the prepare half of a two-step, human-confirmed flow ('Owner confirms in the console'), which tells the agent when to call it. It does not, however, name or contrast against any sibling tool, and no sibling covers deletion, so routing guidance relies on inference.

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