Compare accelerators side by side

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

Annotations only declare readOnlyHint and openWorldHint=false. The description adds real behavioral context beyond that: each cell is cited (sourcing/provenance), unpublished values render as '—' (missing-data handling), and dense vs sparse throughput are kept separate (no aggregation). It does not mention rate limits or latency, but for a read-only tool the disclosure is solid.

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 dense sentences, zero filler. The metric scope and the 2–6 range lead, and the output-format caveat (cited cells, '—' for unpublished) is packed into the trailing clause where it belongs.

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?

There is no output schema, and the description does compensate by describing the return surface (per-metric cells, citations, dash for missing values). The remaining gap is that a portion of the metrics enum and the chip-identifier input format are left for the agent to decode from the raw 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 0%, so the description carries the burden. It partially compensates by enumerating metric families (memory, bandwidth, FP8/BF16/FP4 throughput, power, process) and restating the 2–6 range, but it omits several enum members (memoryType, int8, transistors) and says nothing about the string identifier format expected in 'chips'.

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 (Compare) and resource (accelerators/chips) plus the scope of the comparison (memory, bandwidth, throughput, power, process). It is distinguishable from chip_specs and list_chips by the word 'side by side', though it never names those siblings or explicitly contrasts with them.

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 use case (comparing multiple accelerators at once) is implied by 'side by side' and the 2–6 cardinality, but there is no explicit when-to-use statement and no routing guidance versus chip_specs (single-chip lookup) or list_chips. An agent must infer that this is the multi-chip comparison path.

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