compare_llm_vs_selfhost

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

With no annotations, the description carries the full burden and does substantial work: it states the throughput input 'decides the answer and is never guessed', and it scopes what the self-host number includes by declaring 'Self-host cost is GPU rental only; see honest_gaps' — a real limitation an agent would otherwise misreport. It omits error behavior, data freshness, and what the response contains.

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-loads the core question in one sentence, then the method, then the required input caveat, then examples. Slightly dense with parenthetical asides, but every sentence contributes.

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 10-parameter, no-annotation, no-output-schema tool, the description explains the method and its main limitation but leaves the agent guessing about optional parameter interactions, defaults (targets, api_provider), and the shape of the returned comparison. Adequate to invoke, not complete enough to invoke confidently on the optional surface.

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 70%, so most parameters are already documented. The description adds genuine meaning to output_tokens_per_second (it 'decides the answer and is never guessed') and implicitly to targets (the four clouds), but says nothing about targets semantics, api_provider default behavior, or how monthly_input_tokens versus monthly_output_tokens drive the comparison.

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 concrete verb and resource — prices an LLM API token volume against self-hosted GPU servers across AWS/Azure/GCP/OCI — and explicitly names the third output, break-even volume. That is distinguishable from siblings like compare_token_pricing and compare_gpu_workload, which do not combine API spend with self-host serve capacity.

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?

Three quoted example questions ('should we self-host Llama 3.3 70B instead of paying Together', 'at what volume do H100s beat the DeepSeek API') give clear when-to-use context. It does not name an explicit alternative tool to use instead when the question is only about API pricing or only about GPU pricing, so it stops short of full routing guidance.

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