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

Beyond the generic annotations, the description discloses crucial behavioral details: no backfill, only one watcher allowed per LinkedIn account across workspaces, the agent is created paused, and the workflow includes AI-crafted DM, human review, send, and follow-up rounds. These are exactly the non-obvious behaviors an agent needs to set correct expectations.

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?

Every sentence earns its place: purpose, behavior, constraint, paused state, activation path, advanced alternative, and ID lookup are all packed into a compact, front-loaded description. There is no filler or repetition of schema/annotation details.

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 creation tool with only two simple parameters and no output schema, the description is remarkably complete. It covers what is created, how it behaves, its lifecycle state, uniqueness constraint, activation requirement, and a preferred alternative. The only minor omission is workspaceId semantics, which does not meaningfully undermine an agent's ability to call the tool.

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?

The schema has zero property descriptions, and the description compensates only partially. It explains how to find linkedinAccountId (use campaignstack_list_accounts), but it never explains workspaceId, its optional role, or how workspace scoping interacts with the one-watcher-per-account rule. The parameter names are fairly self-explanatory, but the description does not fully carry the semantic burden.

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 clear verb and resource: 'Create a connection-watch signal agent for a LinkedIn account.' It then defines exactly what the agent does (monitors newly accepted connections, routes them into a welcome workflow) and differentiates the tool from siblings like campaignstack_set_account_watcher and generic signal-agent creators.

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 context: the agent starts paused, must be resumed via campaignstack_resume_signal_agent, and account IDs can be found via campaignstack_list_accounts. It also names an advanced alternative (campaignstack_set_account_watcher) and states when it is preferred, which makes tool selection unambiguous.

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