Delete a call record

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

Beyond the annotations, the description discloses important behavioral details: what is removed (transcript and recording), what is preserved (usage rows), the in-progress restriction, irreversibility, and the required scope. This goes well beyond the structured annotations and gives the agent a complete picture of side effects.

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 core action appears in the first sentence, followed by essential caveats and the scope requirement. Every sentence provides useful information; there is no filler or redundancy.

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?

For a single-parameter destructive tool with annotations already indicating destructive and non-read-only behavior, the description fully covers what is deleted, what is kept, the in-progress limitation, irreversibility, and authorization. Nothing critical is missing for an agent to invoke it correctly.

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 schema already fully documents the single parameter 'id' with a concrete example, so schema coverage is 100%. The description does not add meaningful parameter-level semantics beyond referring to the call record, so the baseline score of 3 is appropriate.

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 a specific verb ('Remove') and resource ('a call log with its transcript and recording'), and clarifies the erasure-request context. It clearly distinguishes itself from sibling tools like hangup_call by noting that in-progress calls cannot be deleted and must be hung up first.

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?

It states when to use the tool ('as a caller's erasure request needs'), when not to use it ('A call still in progress cannot be deleted'), and the prerequisite action ('hang it up first'). This gives an agent clear decision-making guidance without needing to inspect sibling tool definitions.

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