watchlist_delta

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

Annotations already declare readOnlyHint=true. The description adds useful output context (fields returned) but does not clarify how 'last check' is determined or any pagination/rate limits. The behavioral traits beyond read-only are minimal.

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?

Two sentences, no wasted words. Front-loaded with purpose, followed by output summary and usage triggers. Highly efficient and readable.

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 tool with 21 parameters and no output schema, the description lacks details about delta definition, 'last check' semantics, and comprehensive return structure. While it covers core purpose and usage, it is not fully complete for complex filtering scenarios.

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 29%, and the description does not explain the many undocumented parameters. It focuses on output rather than input semantics, leaving agents with little guidance on how to filter or set parameters beyond the few with schema descriptions.

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 it shows changes on the user's sourcing watchlist since last check, with specific output fields (score delta, product identity, fulfillment). It is distinct from sibling watchlist tools like watchlist_list or watchlist_stats, though it does not explicitly differentiate.

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 explicit query triggers ('what changed on my watchlist', 'watchlist updates', 'any changes this week'), giving clear context for when to use. However, it does not mention when not to use or suggest alternatives like watchlist_diff.

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