summarize_call

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

Beyond the annotations, the description discloses three real behaviors: an existing summary is returned rather than regenerated, generation consumes the team's token quota, and the `calls:write` scope is required. The quota/scope disclosure is exactly the kind of cost-and-auth context annotations cannot express, though there is mild tension with idempotentHint=false since reuse implies repeated calls may be free.

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?

Three short, front-loaded lines: what it does, what it costs, what it requires. Every sentence carries distinct information with no 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?

For a one-parameter mutation with no output schema, the cost and auth prerequisites are covered, but the description says nothing about what the returned summary looks like or what happens when a summary cannot be generated (too-short call, unsupported language).

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 description coverage is 0% and the single parameter `id` is never mentioned in the description — it is not stated whether this is a call ID, and no format or error behavior (e.g., invalid/nonexistent call) is given. The agent must infer the target object entirely from the tool name and sibling get_call.

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+resource ('Generate ... AI summary') and clarifies the reuse behavior with '(or return the existing)', which meaningfully distinguishes it from read-only siblings like get_call. It never states that the summary is of a call, leaving the object implicit in 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?

The quota warning implies 'call only when you actually need a summary', which is useful implied guidance, but there is no explicit when-to-use statement and no named alternative (e.g., get_call returning an already-summarized call).

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