Self-test

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

Annotations only supply readOnlyHint=true; the description independently reinforces safety ('Never changes the meter') and adds behavior an agent cannot get elsewhere: the check includes a live reading that can take up to 5 s, and failures are surfaced as SELFTEST_FAILED with measured vs expected values. It does not quantify total runtime or describe the success-path return shape.

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?

Two tight sentences, front-loaded with the read-only nature and then the concrete check list. The enumeration is dense but every item earns its place by telling the agent what a failure could mean; no filler or restated title beyond 'Self-test'.

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 zero-required-parameter, no-output-schema tool, the description covers what is validated and how failure is reported, which is the information an agent needs. The only soft spot is no guidance on reading/acting on the result or on choosing max_wall, minor given the 100% schema coverage.

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 sole parameter max_wall (default 120 s, TIMEOUT on expiry) is already fully documented in the schema. The description says nothing about the time limit or how a 5 s live reading interacts with it, 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?

Names a specific verb and scope ('Read-only health check of adapter, link and meter') and then enumerates exactly what is verified — advertising, connection, meter attached, firmware, ID, display snapshot, live reading within 5 s, batteries. This is clearly distinguishable from data-reading siblings like read, live, status, and query.

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 'health check' framing implies when to reach for it (diagnosing connectivity/setup problems), but there is no explicit when-to-use versus status/live, and no stated prerequisites or exclusions. An agent must infer that this is the diagnostic path rather than the data-retrieval path.

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