get_zerostack_benchmarks

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, and the description still adds real behavior: deterministic offline execution with zero network or hardware I/O, and fail-fast `ValueError` semantics for an unrecognized platform. That failure mode is genuinely new information not present in the annotations or schema, telling an agent an invalid SKU errors rather than returning an empty result. It does not discuss result volume or pagination, but the presence of an output schema reduces that need.

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?

Front-loaded with the purpose, then cleanly sectioned into 'When to use' and 'Behavior' bullets, which makes scanning fast. The parenthetical metric counts (3,255 MAC vectors, 22,959 brownout cut points, 50-router broadcast storms) are dense and slightly ornamental, but they do signal benchmark coverage breadth rather than being pure filler.

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 single-parameter read tool with full annotations and an output schema, the description covers purpose, routing to siblings, execution model and error behavior. Nothing an agent needs in order to call this correctly — or to avoid misrouting — is missing, and return-value detail is correctly left to the output schema.

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% and the schema already enumerates all accepted SKUs, SoC shorthands, wildcards and case-insensitivity, so the description has little room to add. Its only supplementary detail is the error condition for an unmatched platform, which is behavior rather than parameter meaning. Baseline 3 applies since the schema carries the parameter documentation.

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?

Opens with a specific verb and a precise resource/scope: hardware-verified DWT->CYCCNT latency and fault-injection benchmarks keyed by SKU. It enumerates the actual measurement categories (TCLK lookup, NWK encrypt/decrypt, hop ceiling, allocator, Part 2 adversarial metrics) so an agent knows exactly what data class it retrieves, and explicitly separates itself from two named siblings.

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 has an explicit 'When to use' section plus a 'Do NOT use for...' clause naming both alternatives and the condition that selects each (`check_coordinator_capacity` for sizing a user's node count, `analyze_zigbee_thread_log` for log diagnosis). This is the when/when-not/alternative structure at its fullest.

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