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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description greatly enriches these with concrete consequences: which delete_* actions are included, that delete_operation removes the hidden graph flow and run history, that delete_broadcast removes delivery history and content flow, that run_operation sends real broadcasts and writes app variables and cannot be undone, that execution is non-atomic (earlier actions stay applied on mid-batch failure), that resending creates duplicates, and that applying does not publish (draft graph only). It also explains the return shape ({ success, changes, errors, warnings, actionId } plus idRemap). This far exceeds what annotations alone provide.

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?

The description is long (about 40 sentences), but almost every sentence earns its place given the tool's complexity: 26 action kinds, non-atomic execution, destructive side effects, and non-idempotent behavior. It front-loads the core purpose and the validation/atomicity caveats before drilling into the broadcast recipe and deletion warnings. The main structural weakness is that the broadcast recipe and destructive/irreversible sections are packed densely; a top-level 'when NOT to use' or 'destructive actions' heading would improve skimmability, but the content itself is high-value.

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?

This is a high-complexity write tool with a large action enum, no output schema, and no separate validation steps described elsewhere. The description covers: the action contract (via get_action_schema reference), the exact broadcast workflow including scheduling, the full destructive set, the non-idempotency and non-atomicity behavior, the retry guidance, the draft-vs-published distinction (deploy_application), the return shape, and the applicationId scoping rule. There is no missing information an agent would need to select and invoke this tool correctly.

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%, so the baseline is 3 and the bar is lower. The description still adds meaning beyond the schema: it defines the placeholder id convention (flow_1, block_1, var_1, broadcast_1, etc.) for cross-referencing batch items, and it explains the applicationId default behavior ('an application-scoped key defaults to its own application, but a personal key has no default and omitting it fails with MCP_APPLICATION_REQUIRED'). It also clarifies that actions is ordered and non-atomic, complementing the schema's description. Minor gap: it doesn't enumerate every per-action payload rule, but it explicitly defers those to get_action_schema, which is the correct division of labor.

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-resource pair: 'Validate and apply a batch of flow-builder actions' and immediately names it 'the single write path' for editing flows, blocks, variables, broadcasts, sequences, and folders. It clearly distinguishes itself from siblings like validate_actions ('Call this directly; a separate validate_actions call beforehand is unnecessary') and from broadcast-specific tools ('Broadcasts have no dedicated tool and are managed here'). This is a textbook example of purpose clarity.

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 gives explicit when-to-use guidance: it names validate_actions as an unnecessary precursor, tells the agent to read get_action_schema and get_design_guidelines before structural edits, and gives a concrete broadcast recipe ('create_broadcast makes a DRAFT ... a later update_broadcast with status SCHEDULED is what actually schedules/sends it'). It also provides explicit when-not-to-use / caution guidance: confirm deletions with the user, confirm run_operation with the user, never blindly retry a timed-out call that contained run_operation, and re-read state before retrying a failed batch. This goes well beyond any sibling or schema information.

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