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

Annotations already cover the read-only, non-destructive, closed-world safety profile, so the description adds genuinely new behavior: long text is clipped and marked, and the `messages` collection is often absent. That truncation disclosure is exactly the kind of thing an agent cannot learn from structured fields.

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 tight sentences, front-loaded with the action, then the field semantics, then the truncation caveat. No filler and nothing repeated from the schema or annotations.

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?

There is no output schema, so the description carries the return-value burden and does it well: it separates `transcript` from `messages`, warns that `messages` is often empty, and flags clipping. A short note on how to tell clipping occurred or what an absent transcript looks like would make it complete.

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?

With one required parameter at 100% schema coverage, the schema already documents call_id. The description adds no format, sourcing, or example for the id, so baseline 3 applies.

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?

Specific verb and resource: "Fetch one call with its spoken transcript and any message the agent took during it." The singular "one call" implicitly separates it from the sibling list_calls, but no sibling is named explicitly, so the differentiation is inferential rather than stated.

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?

Usage is only implied: needing a single call's transcript. There is no explicit "use this when X" or "use list_calls instead when Y," and no prerequisites or notes about what call_id must come from.

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