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

The description goes far beyond annotations. It details the credit costs, email limits (one per day, 3 total), confirmation requirements for external emails, stop links, idempotent update behavior, and expiration rules. This covers all the operational behaviors an agent needs to understand consequences before calling.

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 very long (over 250 words), covering many nuances. While every detail is relevant, it could be more succinct by grouping related constraints. The core purpose is stated upfront, but the volume of edge cases (limits, costs, confirmation) makes it heavy. Not excessively verbose but borderline.

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 (12 params, no output schema, cost implications, lifecycle rules), the description covers nearly all possible failure modes and edge cases: prerequisites, cost model, idempotency, limits, timezone handling, confirmation flow, and update behavior. It is remarkably comprehensive.

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 schema already documents each parameter. However, the description adds significant value by explaining defaults (3/1.5 for minOutlierScore), relationships between parameters (profileId, URL, handle+platform are alternatives), and the meaning of scoreWindow. It doesn't fully explain every parameter interaction, so 4 rather than 5.

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 creates a viral alert that watches a social media profile and emails when a post's outlier score exceeds a threshold. It distinguishes from related tools like track_profile and crawl_profile by explicitly mentioning them as prerequisites/alternatives, and from delete_viral_alert/list_viral_alerts which are the lifecycle counterparts.

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?

Provides extensive when-to-use guidance: explains the tool is for setting up alerts, identifies prerequisites (profile must be crawled first), explains cost implications, and contrasts with track_profile and crawl_profile. It also covers update behavior (calling again updates settings) which is crucial for correct invocation.

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