voice_ai_get_call_logs

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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, covering the safety profile. The description adds no additional behavioral context—it does not mention pagination, filtering capabilities, return format, or any side effects. Since the description contributes nothing beyond the annotations, it fails to provide extra transparency about what the agent can expect.

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 extremely short—just three words—but it is more under-specified than concise. It lacks any structure or elaboration that would help an agent understand the tool's purpose or output. A concise description should still be informative; this is merely a fragment that duplicates the tool name. There is no front-loading of key details because there are no details.

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 (11 optional parameters, no output schema), the description is drastically inadequate. It does not indicate what the returned list contains, how filtering works, or even that this is a paginated response. With no output schema, the description must at least hint at the return structure, but it is entirely absent. An agent has no idea what data fields to expect or how to interpret the results.

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 100% description coverage per the context signals; every parameter (page, sort, sortBy, agentId, etc.) includes a description. The tool description itself adds no parameter information, but per the rubric, when schema coverage is high, the baseline is 3. The description could have added semantics around how parameters interact (e.g., date filters must be paired), but since the schema already explains this, no deduction is needed.

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 a verb ('List') and a resource ('Call Logs'), making the basic operation evident. However, it does not distinguish this from the sibling tool voice_ai_get_call_log (singular), which could lead to ambiguity about whether this returns a collection vs. a single item. No additional context on the exact scope (e.g., Voice AI call logs) is provided beyond the tool name.

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 is given on when to use this tool versus alternatives such as voice_ai_get_call_log or how it fits into the broader Voice AI workflow. The description lacks any context about prerequisites, typical use cases, or exclusions. An agent must infer from the plural name that this lists all call logs, but no explicit direction is offered.

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