bridge_health

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

With no annotations, the description carries the full burden and handles it reasonably. It discloses that this is a read-only telemetry report pulling real-time data from TD's Perform CHOP, lists the affected metrics, and reveals the optional black/solid output-TOP check. It does not mention permissions or side effects, but the passive diagnostic nature is clear.

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 core value proposition is front-loaded in a single dense first sentence, followed by three compact, single-line parameter definitions. Every line earns its place, and the token-cheap annotation on response_format adds genuine utility without bloat.

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?

Covers the reported metrics, all three parameters with options/defaults, and response granularity via the detail levels. With no output schema, it hints at return structure (summary truncates lists, minimal gives scalar-only) rather than fully specifying it, which is a minor gap given the tool's aggregation complexity.

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 must fully compensate, and it does. Every parameter gets an explicit attainment: output (TOP path for black/solid check), detail (full/summary/minimal with cut-to-25 behavior), and response_format (yaml/json with the token-cheap note). Options and defaults are documented beyond the bare schema types.

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?

States a specific verb and resource ('Show health in one call') and enumerates exactly what is reported: bridge alive/TD frozen/TD gone, REAL fps vs cook rate, frame time vs budget, dropped frames, GPU memory/temp, and mode. This clearly differentiates it from the per-metric sibling tools (measure_fps, measure_gpu, measure_chain) by positioning it as the single aggregated health call.

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 phrase 'in one call' and the consolidated metric list imply this is the go-to aggregated diagnostic versus the granular measure_* tools, but the description never names alternatives or states when NOT to use it. Usage is implied rather than explicit, with no exclusion conditions or sibling routing.

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