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

Annotations only state readOnlyHint=false, openWorldHint=false, idempotentHint=false, destructiveHint=false, so the description adds real behavioral value by disclosing that observations are appended (a side effect) and that failures are listed for follow-up. It also explains what the tool returns, which is useful given there is no output schema. It stops short of discussing rate limits or authorization, but those gaps are minor.

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 tightly written sentences deliver the core purpose, behavior, return values, failure handling, and follow-up action without wasted words. The critical 'only tool that re-reads prices' message is front-loaded, and each clause contributes necessary 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 no output schema, the description adequately covers return values and failure behavior. It differentiates the tool from siblings, explains the state-changing 'appends observations' behavior, and routes the agent to alerts_pending. With only two optional parameters fully documented in the schema, nothing essential is missing for correct invocation.

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 description coverage is 100%, and the schema already documents both parameters in detail, including the 'id or URL' format, the 'all=true' behavior, and the free-tier restriction. The main description only repeats 'one watch or all' and adds no additional parameter-level nuance, so a baseline score of 3 is appropriate.

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 states a specific verb ('re-reads prices') and resource ('one watch or all'), and explicitly claims it is 'the only tool' that does this, distinguishing it from siblings like price_check and price_history. It also enumerates the returned fields (current, previous, min, max, change %, target hits), making the tool's purpose unmistakable.

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 positions the tool as the sole mechanism for refreshing prices and instructs the agent to follow up with alerts_pending when a page fails. The schema's id description further reinforces when to call ('whenever the user asks about prices, drops or alerts') and that nothing runs in the background, providing clear contextual usage guidance.

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