watchlist_diff

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

Annotations already declare readOnlyHint=true, indicating a safe read operation. The description adds that the tool shows changes and that it requires a baseline (set by watchlist_add), enhancing transparency. However, it does not disclose behaviors like pagination, data volume limits, or authentication requirements, which would be useful for an agent.

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 concise, with three sentences and a usage tip, all front-loaded with the core purpose. Every sentence adds value: purpose, output details, example queries, and a note about the baseline. There is no redundancy or unnecessary 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 tool's complexity (24 parameters, no output schema, many siblings), the description covers the core purpose and output fields but lacks details on the return format, pagination, and how the numerous filter parameters interact. The baseline concept is mentioned but not fully explained. It is adequate for basic use but could be more complete to handle 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?

With schema description coverage at only 25%, the description should compensate by explaining the numerous filter parameters. While the description mentions the output fields (new sellers, score moves, product identity, fulfillment), it does not elaborate on how the input parameters (e.g., min_new_sellers, product_brand_contains) affect the results. The overall context helps but does not provide sufficient parameter-level guidance.

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: 'Show what changed on a saved tracking list versus its captured baseline', specifying the verb 'show', the resource 'tracking list', and the action 'diff against baseline'. It also details the output (new sellers, score moves, product identity, fulfillment) and provides example user queries, distinguishing it from related tools like watchlist_add.

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 explicit usage context with example queries ('what changed on <list>', 'any updates on my watchlist') and directs the user to an alternative tool ('Re-run watchlist_add to reset the baseline'). It does not explicitly state when not to use this tool, but the examples adequately guide the agent.

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