mqtt_subscribe

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

The description explicitly discloses a critical behavioral trait: 'returns an error' because it is 'not yet implemented.' This goes far beyond what annotations (none provided) would convey. It honestly tells the agent that any invocation will fail, which is exactly the kind of behavior an agent needs to know. There is no ambiguity about the tool's current executability.

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 two short sentences, with the core action front-loaded and the critical caveat immediately following. Every word earns its place: the first sentence states the intended purpose, the second explicitly warns of non-implementation and the resulting error. There is no fluff, redundancy, or unnecessary detail, making it highly efficient for an agent to parse.

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?

For a stub tool with a single parameter and no annotations, the description is largely complete: it tells the agent the tool is not functional and will return an error, which is the most important fact. The output schema exists, so detailed return values are not the description's responsibility. The only gap is the absence of any guidance on what to do instead (e.g., no mention of an alternative subscription tool or a future implementation date), but this is a minor omission given the tool is clearly non-functional.

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 contains one parameter, 'topic_pattern,' with no schema-level description (0% coverage). The tool description says 'Subscribe to MQTT topic pattern,' which essentially restates the parameter name without adding semantics. It does not explain MQTT wildcard syntax (e.g., '+', '#'), the expected format, or any constraints on the pattern. Given the lack of schema coverage, the description fails to compensate, providing minimal added meaning beyond the parameter name.

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 identifies the intended operation: 'Subscribe to MQTT topic pattern.' This uses a specific verb ('subscribe') and resource ('MQTT topic pattern'), and distinguishes it from siblings like mqtt_connect and mqtt_disconnect by naming a different action. However, the immediate disclaimer 'Not yet implemented - returns an error' tempers the clarity; the agent must reconcile the stated purpose with the actual non-functional behavior. It is not a tautology, and enough detail exists to understand the tool's intent.

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 provides an implicit usage guideline: since the tool is not yet implemented and returns an error, it should not be relied upon for actual MQTT subscriptions. However, it does not explicitly say 'do not use' or recommend any alternative tool or workflow. 'Not yet implemented' implies the agent should avoid calling it, but no when/when-not conditions or sibling alternatives are mentioned, leaving the agent to infer that this tool is currently a stub.

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