update_watch

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

The description explicitly notes 'MUTATES' and provides critical behavioral details: changing criteria replaces the definition and clears pending hits, with repopulation on next daily eval. It also mentions the required SF_API_KEY. Without annotations, the description fully carries the burden of behavioral disclosure.

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?

The description is a single paragraph but effectively front-loads the purpose and includes necessary behavioral details. It could be slightly more structured, but it remains focused and not overly verbose.

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?

Given the tool's complexity (6 parameters, nested objects, no output schema), the description adequately covers mutation consequences, pending hit clearing, and a recommendation to preview. It lacks return value details, but that is acceptable without an output schema.

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 the baseline is 3. The description adds value by summarizing update options and advising to use preview_watch first, which is not in the schema. It also clarifies the watch identification alternatives.

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 clearly states the tool updates an existing watch in place, listing specific actions: rename, change novelty_min, or retarget its structured filter criteria. It also mentions addressing by watch_id or name, which distinguishes it from create_watch and delete_watch.

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 provides guidance on identifying the watch via watch_id or name and recommends tuning new criteria with preview_watch first. However, it does not explicitly state when not to use this tool versus alternatives like check_watches.

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