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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantial behavioral context beyond that: default/max limits, byte bounds, concatenation rules, interruption-state preservation, cursor restart behavior, independence of state/sourceComplete from pagination, and handling of missing/disabled/expired/deleted artifacts. This is a model of transparent behavior disclosure.

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?

Every sentence adds necessary operational detail: purpose first, then auth, then limits, then pagination and edge cases. There is no repetition of the tool name, no filler, and the structure front-loads the most critical selection information before diving into pagination mechanics.

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 paginated read tool with an output schema, the description is complete: it covers auth requirements, pagination semantics, cursor handling, limits, and degenerate artifact states. The output schema already documents return structure, so the description does not need to restate response fields, and nothing necessary for correct invocation is missing.

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%, so the description carries the burden for parameter meaning. It adds real value by explaining the limit default (100) and max (500), the need for a call ID, and cursor staleness/restart behavior. It does not name the parameters explicitly, but an agent can map 'call ID', 'max 500 fragments', and 'stale cursor' to callId, limit, and cursor without difficulty.

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 opens with a specific verb and resource: 'Read retained spoken turns for one internal WhatsApp call ID.' This clearly distinguishes it from sibling tools like get_whatsapp_call (metadata) and download_whatsapp_call_recording (audio), so an agent can tell exactly what operation this performs without guessing.

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 clearly establishes that this tool reads transcript content for a single call and requires ownership/read scope. It does not explicitly name alternative tools or state when not to use it, but the focused 'spoken turns' wording makes the appropriate context unambiguous enough for selection among siblings.

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