Refresh prices

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

With no annotations, the description carries the burden. It discloses that it re-fetches, appends new observations (a write operation), and returns specific metrics. However, it does not mention potential side effects like generating alerts, rate limits, or whether it is long-running. The schema description adds 'Nothing runs in the background', but that is not in the main description.

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 a single sentence that front-loads the purpose ('This is what actually checks prices') and then lists the key behaviors and return values. It is concise and every clause adds value, though it could be split into clearer sentences for readability.

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?

The description explains what the tool does and what it returns, which covers the core functionality. However, it omits important contextual details like the recommended usage pattern (call once per session, then read alerts_pending) which is only present in the schema description. There is no output schema, so the return fields are described, but side effects or prerequisites are not fully addressed.

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?

The input schema covers 100% of the parameters (id and all) with clear descriptions. The description adds little beyond the schema: it mentions 'one watch or every watch' which mirrors the schema. No extra parameter-specific semantics are provided.

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 action: 're-fetches one watch or every watch' and the resource 'watch'. It lists the exact return data (current, previous, min, max, change %, extraction confidence, target hits), making it distinct from siblings like price_check (likely a one-off check) or price_history (likely returns historical data without refreshing).

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 only hints at usage with 'This is what actually checks prices' but does not explicitly state when to use this tool vs alternatives or mention exclusions. However, the parameter schema for 'id' includes guidance ('call this whenever the user asks about prices, drops or alerts - typically once at the start of a session, then read alerts_pending'), which is part of the tool definition but not in the main description text.

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