Get calls summary

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

Annotations declare readOnlyHint=true, which aligns with 'summarize' implying a read operation. No contradiction. Description adds no further behavioral traits (e.g., output format, pagination, rate limits). Minimal extra value beyond annotations.

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?

Single concise sentence that front-loads the core purpose. Efficient, but could benefit from minor restructuring 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?

No output schema, but description fails to describe what the summary returns (e.g., counts, averages, breakdowns). Users are left to guess the response format. Incomplete for a summarization tool with 6 parameters.

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 coverage is 67% (4/6 params described). Description enumerates valid group_by options, which parallels the schema enum, adding some context. However, it does not explain the interplay of date_range vs start_date/end_date or the purpose of company_id. Moderate value added.

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?

Description clearly states 'summarize call data grouped by a dimension' with specific verb and resource. Lists all valid grouping options, distinguishing from sibling tools like list_calls (raw data) and get_calls_timeseries (time-series).

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?

No guidance on when to use this tool vs alternatives. Does not mention exclusions, prerequisites, or typical use cases. Given 33 sibling tools, this is a significant gap.

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