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

Annotations already declare readOnlyHint and idempotentHint, covering the safety profile. The description adds useful behavioral nuance by disclosing that message and connection watch agents return a watcherActivity block because they produce no signal events. This explains conditional output behavior beyond what annotations provide, though it does not cover potential staleness, authentication, or rate limits.

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 sentences with no filler. The main metric list is front-loaded, the conditional watcherActivity explanation earns its place, and the pointer to list_signal_agents is a practical final sentence. Every sentence contributes useful 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?

For a single-parameter read-only metrics tool, the description is largely complete: it identifies the resource, enumerates return metrics, explains a conditional output block, and tells how to obtain valid agent IDs. It stops short of describing pagination, timezone behavior, or explicit handling for non-watch agent types, but those are minor given the simple scope.

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 carries the burden. It explains that the only parameter, agentId, refers to a signal agent and directs the user to campaignstack_list_signal_agents to find valid IDs. This adds meaningful context beyond the raw schema definition (string, minLength 1), but it does not elaborate on ID format or any edge cases.

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 'Get dashboard metrics for a signal agent' and enumerates specific metrics (total signals, last-24h signals, leads created, posts watched, priority breakdown). This is a precise verb+resource statement and the metric list clearly distinguishes it from related tools like campaignstack_get_signal_agent or campaignstack_list_signal_agents.

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 clearly implies when to use the tool (when dashboard metrics for a signal agent are needed) and gives an explicit cross-reference: 'Use campaignstack_list_signal_agents to find agent IDs.' However, it does not explicitly state alternatives or exclusions relative to other 'get' tools, such as when not to use it vs campaignstack_get_signal_agent.

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