fleet_health

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

With no annotations provided, the description carries the burden of behavioral disclosure. It does explain the meaning of `stranded` and the presence of worker heartbeats, which adds useful semantic context. However, it does not state whether the tool is read-only, how it handles missing app_id, or the exact structure of the response beyond the mentioned fields.

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 concise (about 70 words) and front-loaded with a clear summary. The second paragraph adds meaningful explanation of the stranded-task concept without unnecessary verbosity. Every sentence contributes 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?

The description explains key concepts and mentions the output fields (`pending`, `workers`, `stranded`), but the lack of an output schema means the response format is unclear. It also doesn't describe the data source, the meaning of 'counts by status' in terms of actual fields, or the effect of app_id. Given the tool's moderate complexity, the description is adequate but has notable gaps.

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 input schema has one parameter, `app_id`, with 0% description coverage. The description never mentions `app_id` or explains what it refers to or how it scopes the health data. Although the parameter name is suggestive, the description adds no semantic value to it.

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 tool's function: 'task queue counts by status, plus live worker heartbeats.' It distinguishes from siblings like task_list or fleet_status by emphasizing fleet-level health monitoring and the stranded-task concept.

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 implies usage for understanding queue health and provides conceptual context ('a queue depth is only half the picture'), but it does not explicitly state when to use this tool versus alternatives or mention any exclusions. No direct comparison to sibling tools is made.

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