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

Annotations flag destructiveHint=true, but the description adds the crucial operational detail: this is a REAL ACTION, not a preview, the new goal will be spoken to a real person, and explicit confirmation is required just before the call. It also narrows applicability to queued calls, which annotations cannot express.

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?

Five short sentences ordered by importance: action, ID source, safety, real-world effect, confirmation. No redundant phrasing and the escalation ('REAL ACTION') is placed prominently.

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 two-parameter mutation with no output schema, the description covers action, prerequisites, safety, and confirmation well. It does not say what happens on failure (e.g., call already in progress) or what the call returns, a minor gap.

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 100% and the goal parameter's description already explains replacement semantics and safety rules. The tool description adds only 'Show the exact new goal', so it does not meaningfully extend what the schema provides; 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?

States a specific verb and resource with scope: 'Update the goal of one queued outbound call in place.' An agent can tell immediately this edits an existing scheduled call's goal, not a new call (scheduleCall) or other call mutations.

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?

Gives the precondition ('Use a call ID returned by getCallHistory') and the safety gate ('Refuse the same harmful goals as scheduleCall'), plus an operational rule to confirm with the user before acting. The only gap is the absence of an explicit when-not-to-use case beyond harmful goals.

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