Real-time readings

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

Annotations only declare readOnlyHint=true; the description adds meaningful behavior: the ~4 Hz sampling rate, that results are aggregated not streamed, the exact summary fields returned (count, rate, first/last time, min/max/mean, functions/units, last 5 readings), and the default window. It does not discuss adapter error behavior or what happens if the adapter is disconnected.

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 action, sampling rate, stop conditions, and return shape are front-loaded in one dense sentence, with the routing hint to log_start placed last. The enumeration of summary fields is long but earns its place since there is no output schema.

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?

With no output schema, the description carries the return-value burden and does so thoroughly, listing every summary field. Combined with the sampling rate, entry conditions, defaults, and the log_start alternative, an agent has everything needed to call it correctly.

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 coverage is 100%, so all three parameters are already documented, including the count/seconds 'whichever comes first' semantics. The description restates the default of 20 readings and the count-or-seconds choice but never mentions max_wall and adds no syntax or interaction detail beyond the schema, so baseline 3 applies.

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 ('Collect real-time readings from the adapter'), the sampling rate (~4/second), and crucially that it returns a summary rather than raw readings. The contrast with log_start makes it distinguishable from the closest sibling without opening either schema.

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?

Explicitly routes long-running or file-persisting cases to log_start, which is the key disambiguation for this tool, and gives the default of 20 readings. It does not differentiate from other siblings such as read, query, or status, so the guidance is clear but not exhaustive.

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