Refresh prices

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

With no annotations provided, the description must disclose behavior itself. It states the tool re-fetches, appends observations (mutation), returns multiple metrics, lists failing pages, and recommends reading alerts_pending next. It also implies nothing runs in the background via schema. This is substantial behavioral context, though it does not explicitly state that it modifies state (appending observations is implied).

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 two sentences, front-loaded with the core purpose ('The only tool that re-reads prices') and efficiently lists outputs, failure behavior, and next step. No fluff; every clause earns its place.

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 clearly enumerates return values (current, previous, min, max, change %, target hits) and failure handling (failing page listed, then read alerts_pending). It covers operational flow and next steps. A stronger description might mention rate limits or permission requirements, but for this tool's complexity, it is complete enough.

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 both parameter descriptions are detailed, especially 'id' which explains omission semantics and usage timing. The main description adds marginal value beyond schema (e.g., 'one watch or all' maps to id/all) but does not introduce new parameter meaning. Baseline 3 is appropriate as schema does the heavy lifting.

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 uses a specific verb ('re-reads prices') and resource ('one watch or all'), lists concrete outputs (current, previous, min, max, change %, target hits), and explicitly claims to be 'the only tool' that re-reads prices, distinguishing it from siblings like price_check and price_history. It also mentions failure listing and a follow-up, making 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 provides context ('whenever the user asks about prices, drops or alerts' appears in schema, not main text) and directs to read alerts_pending after, but does not explicitly list exclusions or when NOT to use this tool versus alternatives. The phrase 'the only tool' and schema hint cover typical usage scenarios adequately, but the main description lacks explicit when-to-use guidance beyond implication.

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