Read a bounded time series

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 does disclose two notable behaviors: deterministic cursor pagination (stable pagination across requests) and automatic stream downsampling (data resolution may be automatically reduced). However, it omits other pertinent behaviors such as ordering, limits, error handling, or the meaning of 'bounded' in the title. Some transparency is provided, but critical gaps remain.

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, compact sentence of 11 words. It is front-loaded with the core action ('Read') and packs three meaningful concepts (read, pagination, downsampling) without any wasted words. Every phrase 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 the tool's complexity (9 parameters, no output schema, no annotations), this description is too sparse. It does not describe the response format, how filters interact with series, whether startDate/endDate are required despite being optional in the schema, or what 'bounded' means in practice. A single sentence is insufficient for an agent to safely invoke this tool with a correct mental model of its behavior.

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 has 0% description coverage, so the description must compensate. It does add meaning to several parameters: 'cataloged' hints at dataset semantics, 'numeric series' clarifies metrics, 'pagination' relates to cursor and pageSize, and 'downsampling' explains resolution. However, it leaves filters, startDate/endDate, activityId, and other parameters unexplained. The description adds some value but does not fully compensate for the missing schema descriptions.

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 the verb 'Read' with a specific resource ('cataloged numeric series') and adds distinctive features ('deterministic cursor pagination', 'automatic stream downsampling'). It clearly differentiates from siblings like aggregate_data, analyze_series, and fit_series_model, which imply transformation or modeling rather than raw data access.

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 implies a read operation for cataloged numeric series, suggesting it is the tool for fetching time series data. However, it does not explicitly state when to use this tool versus alternatives like query_read_only_data or describe_dataset, nor does it provide exclusion criteria. The usage context is implied but not articulated.

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