telemetry_subscribe

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

With no annotations, the description carries the full burden for disclosing side effects. It mentions caching of latest values but does not specify whether the subscription persists across sessions, if it consumes resources, or if it requires explicit cleanup. The description is adequate but lacks depth on behavioral implications beyond the basic subscription lifecycle.

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: a two-sentence overview followed by a list of parameters, each described in one line. No redundant words or filler. The most critical information (what the tool does and how to use its results) appears first.

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 covers the core workflow (subscribe and query) and parameter meanings. With an output schema available (as indicated by context signals), it is not required to detail return values. However, it omits edge cases like invalid paths, duplicate subscriptions, or error handling, which a more complete guide would address.

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 0% description coverage, so the description must compensate. It provides meaningful but brief explanations for all three parameters: 'device' as defined in devices.yaml, 'paths' as comma-separated telemetry path names or OpenConfig paths, and 'interval_ms' as collection interval with default. This adds value beyond the bare schema, though more detail on acceptable path formats would help.

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 'start[s] a gNMI streaming telemetry subscription' for a device, then explains it subscribes to OpenConfig paths and caches values for later querying. This specific verb+resource framing distinguishes it from sibling tools like telemetry_query (reads data) and telemetry_unsubscribe (stops subscription).

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 tells the agent to 'Use telemetry_query to read collected data,' providing a clear next step after subscription. While it does not explicitly state when not to use it or list alternatives, the separation of concerns among siblings (subscribe, query, unsubscribe, list) is implied by the description's focus on starting a subscription.

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