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

Even though annotations already flag destructiveHint=true, the description adds detailed behavioral context: stops polling, pauses linked workflow, disables watched posts, clears competitor watch linkage, and is recoverable with data retained and visible via includeArchived. This goes well beyond the annotations and paints a complete picture of side effects and reversibility.

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 three efficient sentences: first states the action and effects, second explains when to use it and the recoverability, third names the alternative and the ID-lookup tool. Every sentence earns its place, and the most important information is front-loaded.

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?

Given one parameter, an output schema, and annotations covering safety, the description is complete. It explains the operational consequences, the difference from pausing/deleting, the recovery behavior, and how to obtain the agent ID. An agent can correctly select and invoke this tool without further research.

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?

There is only one parameter (agentId) and the schema provides no description, so the description must compensate at 0% coverage. It does not explicitly define agentId, but the tool name and opening sentence make the semantic clear, and it provides a concrete way to obtain valid values ('Use campaignstack_list_signal_agents to find agent IDs'). This is sufficient for a single obvious parameter.

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 and resource ('Archive a signal agent') and enumerates exactly what archiving does (stops polling, pauses workflow, disables watched posts, clears competitor watch linkage). It explicitly distinguishes itself from pausing and deleting, leaving no ambiguity about the tool's purpose relative to siblings.

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 an explicit when-to-use condition ('when the user asks to shut a watcher down for good rather than pause it for a while') and names the alternative tool for temporary stops (campaignstack_pause_signal_agent). It also directs the agent to campaignstack_list_signal_agents for finding agent IDs, so the invocation path is fully covered.

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