summarize_measurement

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

The description discloses some behavioral details, such as using DataFrameClient.query_decimated_data on a live server and not downloading every row, which implies a performance-oriented approach. However, it does not explicitly state side effects, error conditions, or whether the operation is read-only. The mention of 'downsampled trace preview' and 'stats' gives partial transparency but could be more explicit.

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 concise, with the main explanation in two sentences and then a brief parameter breakdown. While the parameter list is repeated in the schema, it adds clarity without being overly verbose. The structure is logically organized and easy to parse.

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 does not specify the output format or structure of the summary, nor does it mention potential errors or edge cases (e.g., what happens if neither table_id nor result_id is provided). Given the lack of an output schema, the description could be more complete by explaining what the returned stats and trace preview contain.

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 description provides helpful explanations for each parameter (table_id, result_id, preview_limit) that go beyond the schema. It clarifies the relationship between table_id and result_id (result_id is used if table_id is omitted) and defines preview_limit as a capped maximum. Since the schema itself lacks descriptions, this added semantic information is valuable.

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 tool's function: summarizing a measurement table with stats and a downsampled trace preview. It is specific about the resource (measurement table) and the action (summarize), though it does not explicitly distinguish itself from sibling tools like summarize_yield, which might also produce summaries.

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 guidance on how to use parameters (e.g., 'Pass table_id directly, or result_id to use the first attached data table') but lacks explicit direction on when to choose this tool over alternatives such as summarize_yield or query_results. There is no mention of scenarios or prerequisites for using this tool instead of others.

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