bridge_status

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. The description lists the output fields (alive, age, project, build) but does not disclose whether the tool performs any side effects (it appears read-only, but that is not stated), whether it can block or timeout (if the bridge is down, does it hang or return error?), or what the actual return format is. It also does not mention any error handling or connection requirements. For a status tool that might be used in health checks, this transparency is insufficient.

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 and front-loaded: 'Bridge heartbeat state' immediately conveys the essence, followed by a list of key fields. It is a single sentence without fluff. It could be slightly improved by adding a period and perhaps more detail, but it is efficient and structurally sound for its purpose.

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 tool has no parameters, no output schema, and no annotations. The description lists the output fields but does not explain their types (e.g., 'alive' likely boolean, 'age' integer) or the response format (JSON? text?). An agent calling this tool would need to know the output structure to use it effectively. Also, given the complexity of sibling tools (many bridge_* tools), the description does not clarify how this status tool fits into workflows, such as when to use it before calling bridge_send or bridge_ensure_alive. The description is too minimal for a complete picture.

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 tool has zero parameters, and the schema coverage is 100% (the schema is empty, so all parameters are documented). With no parameters, the description does not need to explain parameter behavior. The description adds value by clarifying the output fields, which is useful for interpretation, but since there are no inputs, the parameter semantics dimension is mostly satisfied by the absence of parameters, which the description confirms by not mentioning any.

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 purpose: to provide the bridge heartbeat state, including specific fields like alive status, age in seconds, project, and build. This distinguishes it from the sibling tool 'bridge_state' which likely returns a general state, but the description does not explicitly differentiate it. The verb 'heartbeat state' is specific enough to convey a health-check function, making it a clear, though not deeply differentiated, purpose.

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 checking bridge liveness via the 'alive' field and age, but it does not explicitly state when to use this tool versus alternatives like 'bridge_state' or 'bridge_ensure_alive'. There is no guidance on when to check status versus when to take action, and no mention of pre-conditions or typical scenarios. The context signal of zero parameters suggests a simple call, but the lack of explicit usage context and alternatives is a gap.

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