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

Annotations already cover readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the description's additional disclosure about summary generation ('generated once on first read after post-call processing and cached') adds valuable behavioral nuance about timing and caching. This goes beyond the annotations without contradicting them.

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?

Two sentences with no filler. The first sentence front-loads the core return fields; the second adds the behavioral nuance about summary caching. Could potentially split the field list for scannability, but overall it uses every word efficiently.

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?

The tool has an output schema and annotations cover safety and idempotency, reducing the description's burden. The description covers the key fields and the summary behavior. It doesn't mention how to obtain the call ID or pagination, but neither is necessary for a single-get tool with one parameter.

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 provides 100% coverage and unambiguously documents the only parameter (id: 'The call ID.'). The description adds no new parameter-specific details beyond the obvious, so a 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 states a specific verb ('Get'), resource ('phone call'), scope ('single'), and enumerates the exact fields returned (status, duration, participants, AI summary components, quality score). This clearly distinguishes it from sibling tools like phone_call_list, phone_call_recording_get, and phone_call_transcript_get.

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 description implies when to use this tool — when a caller needs the full detail of a single call, especially the AI summary and quality score. However, it does not explicitly name alternatives or state when not to use it (e.g., phone_call_list for browsing calls), leaving a small inference step.

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