preview_watch

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

With no annotations provided, the description carries the full burden. It discloses that the tool is read-only, requires SF_API_KEY, and details the match_count cap at 200 for similarity filters, along with how to interpret sample scores. This is comprehensive behavioral insight.

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 fairly detailed but well-structured, starting with the core purpose and then adding nuanced behavioral notes. While every sentence adds value, it could be slightly more concise without losing information.

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 complexity of the input schema (nested criteria) and no output schema, the description provides important return structure hints and a critical caveat about saturation. It covers key points but could detail error cases or more examples.

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 baseline is 3. The description adds significant value beyond the schema by explaining the match_count cap, the similarity floor default adjustment, and the 'cites' relation window. This goes beyond mere repetition.

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's purpose as a dry-run or preview for structured filters, using the phrase 'without creating a watch — the tuning loop.' It distinguishes from sibling tools like create_watch and update_watch by emphasizing the iterative testing nature.

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 explicitly explains when to use this tool (before saving, to iterate) and provides guidance on not relying on match_count for similarity filters, directing users to tune using sample scores and narrowing criteria. This provides clear usage context and alternatives.

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