audience_manage_prepare

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

With readOnlyHint=false and destructiveHint=false already given, the description adds genuinely useful behavioral context: the approval is 'Bound to principal, account and exact request' and 'nothing is sent'. That dry-run scope is non-obvious and cannot be inferred from the annotations, which would otherwise leave the safety profile ambiguous.

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?

A single dense sentence with the core action front-loaded and the safety constraint after a semicolon. No filler; every clause carries information.

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?

An output schema exists, so return values need not be described, and the annotations cover the mutation profile. However, for a two-phase-commit entry point the description omits the approval lifecycle (what happens after, which tool applies it) and the operation vocabulary, leaving gaps an agent must guess at.

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 must carry the parameter meaning. It partially does by listing the arg keys ('ids, query, body, csv'), but the required 'operation' parameter and its allowlisted values are never explained, leaving the required field undocumented in both schema and description.

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 pairs a specific verb with a specific resource: 'Open an approval for one allowlisted Audience write/upload'. This tells the agent it stages a request rather than performing it, distinguishing it in spirit from the apply/reconcile siblings. It stops short of explicitly naming the sibling tools it hands off to.

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?

There is no explicit statement of when to use this versus audience_manage_read, audience_manage_apply, or audience_manage_reconcile. The prepare/apply pattern is only implied by the word 'approval'. No prerequisites or exclusions are stated.

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