mesh_watch

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

No annotations were provided, so the description carries the full burden. It clearly discloses the blocking nature ('This call BLOCKS for the full duration (or until count events arrive)'), the lack of background subscription ('there is no standing/background subscription to poll later'), the host default, and the lifecycle guidance (call again to keep watching). These are critical behaviors for an agent to know before invoking the tool.

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?

Three short sentences each earn their place: first defines the core action, second explains blocking semantics and third routing, and third handles a common edge case (presence heartbeats). No filler, and the most important behavioral detail is front-loaded.

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 is complex due to its blocking nature and early-exit conditions, and the description covers those well. There is no output schema, and the description only says 'return whatever arrived', which is somewhat vague about the exact shape of the returned data. Still, the openness reinforces it's a watch/listen operation, and with the codec/domain context from the MCP tool family, it is adequately complete for an agent to understand basic flow.

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 100%, so the baseline is 3. The description does add some behavioral nuance to parameters (e.g., that duration_seconds sets the max blocking window and count allows early exit, and that host has a default), but most of this is already present in the schema. It is useful but not redundant.

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 states a specific verb and resource (watch a mesh topic for inbound facts), and explicitly distinguishes the tool by clarifying there is no standing subscription, with an alternative provided ('watch ... instead of polling mesh_agents'). This clearly separates it from sibling tools.

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?

It provides a concrete when-to-use statement (blocking watch of a topic) and gives an explicit exclusions: 'Presence blogs are ordinary facts on agent.hello/agent.goodbye -- watch those directly ... instead of polling mesh_agents.' While it doesn't cover when to use versus every sibling, it does offer enough routing for a key alternative.

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