Generate a call summary

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

Adds substantial behavior beyond the annotations: async queue-and-return semantics, required scopes (call_events:write, luca:draft), full_content sensitivity, and the Idempotency-Key requirement with the fallback that the server generates one. This is useful operational context even though annotations already flag destructiveHint=true.

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?

Front-loads the most important fact (queued, returns immediately, poll for result) in the first sentence, then lists operation/scope/idempotency details compactly. Every line carries useful information with minimal waste.

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?

An output schema exists so return values need not be explained, and the description covers async behavior, scopes, idempotency, and workspace targeting. The only gap is the lack of contrast with the sibling summary_replace tool.

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 75% and the description reinforces the tricky parts: 'Provide idempotencyKey for safe retries, or the server will generate one' and 'Use workspaceId or workspaceSlug to override the default workspace'. It adds retry/override intent beyond the raw 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?

States a specific verb+resource ('Generate a call summary') and adds the crucial async detail that it queues work and returns immediately. It doesn't explicitly name or contrast with the sibling luca_call_events_summary_replace, so an agent must infer which of the two summary tools to pick.

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 'Poll the call event for the result' line gives clear workflow context for how to obtain the result. However, there is no explicit when-to-use guidance versus luca_call_events_summary_replace or other summary-related siblings, leaving the choice to inference.

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