get_history

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It exposes a key limitation: 'Free tier returns the last 7 days; Pro returns everything.' This is important behavioral context. It also clarifies the content returned and the window-based nature of the request. However, it omits details such as how the 'days' parameter interacts with the free tier limit (e.g., clamping or error) and whether there are any pagination or rate limits. Still, for a basic read operation, it adds meaningful transparency beyond the name.

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 compact and front-loaded. The first sentence immediately states the tool's purpose and beneficiary ('so Claude can surface trends'). The following sentences add value: data types, use cases, and tier limit. No sentence is wasted, and the structure is easy to scan. It achieves high informational density in a few lines.

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 simplicity (one optional parameter, no output schema) and the presence of useful sibling context, the description is fairly complete. It covers what data is returned, typical use cases, and the free/pro tier distinction. The main gaps are the lack of detail about how 'days' maps to the window and how the system handles requests that exceed the free tier limit. These are minor for a straightforward read tool, so it earns a 4 rather than a 5.

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 0%—the description never mentions the 'days' parameter. It says 'over the requested window' but does not explicitly tie that to the 'days' parameter or explain how it behaves (e.g., default of 30, whether it is a count of days back or a specific date range). Given low coverage, the description was expected to compensate but does not. The parameter is simple, but the connection is missing.

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 clear verb and resource: 'Return the full time-series history.' It explicitly lists the data types included (daily check-in snapshots, revenue by day, calendar load), and the phrase 'so Claude can surface trends' clarifies the tool's intended role. This distinguishes it from siblings that log or ingest data (log_checkin, ingest_revenue_event) and from tempo_score or weekly_digest, which are more summary-oriented. The scope is unambiguous.

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 concrete usage context: 'Useful for building sparklines, comparing weeks, or asking "am I actually getting better?"' This signals when to invoke the tool for trend analysis. It does not explicitly name alternatives or state when not to use it, but the sibling tool list makes it clear that other tools handle data input or summaries. The guidance is present but not exhaustive.

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