cigchat_cancel_broadcast

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

With no annotations, the description carries the full burden and does well. It explicitly labels the operation as 'DESTRUCTIVE: irreversible' and explains the two-phase confirmation flow to get an impact statement before permanent action. It also disloses the required authorization scope. This gives the agent clear expectations about side effects and safety.

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 compact and well-structured. It leads with the action, immediately highlights destructive consequences, then gives the confirmation procedure and scope requirement. Every sentence serves a clear purpose, and no filler exists. The warning is front-loaded, which is appropriate for a destructive operation.

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?

The description covers the critical destructive/confirmation context, but it misses the meaning of the required 'broadcast_ns' parameter entirelyikuha. Additionally, with several broadcast-related siblings, it does not explicitly distinguish when to use this cancel operation versus deleting a broadcast. Its completeness is adequate for the core action but incomplete for parameter-level and alternative-based decision making.

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 50%: only 'confirm' has a description, and the tool description reinforces that flow. However, 'broadcast_ns' is required but completely undocumented in both the schema and the description. The phrase 'current flow' gives a vague hint but does not define what a broadcast namespace is or how to obtain it. With low coverage, the description should compensate but does not.

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 clearly states the specific action: 'Cancel all pending recipients of a new, scheduled, or sending broadcast in the current flow.' It precisely identifies the resource (broadcast) and the verb (cancel), and the scope ('current flow') distinguishes it from a global delete. The sibling 'cigchat_delete_broadcast' suggests a related but different operation, and this description makes the distinction clear enough.

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 usage instructions: 'Call once without `confirm` to get an impact statement first' and requires the 'Send Message' scope on the token. This is clear operational guidance. However, it does not explicitly exclude cases where it should not be used (e.g., if the broadcast is already completely sent) or mention alternatives like 'cigchat_delete_broadcast' for full deletion.

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