describe_engine_capabilities

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds that responses carry an accuracy_tier that varies by engine, which is useful context, but it says nothing about caching, latency, or whether capability data is stable across calls.

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 short sentences, front-loaded with the action and followed by the invocation order. Nothing is redundant or padded.

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?

An output schema exists, so the description need not explain return values, and it correctly covers purpose and call ordering. It could go slightly further by indicating what the accuracy_tier levels imply for downstream trust, but nothing essential is missing.

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%, but the single parameter is an enum (bigquery/snowflake/databricks) whose meaning is self-evident, and the description identifies it as 'the given warehouse engine'. It adds no format or constraint detail beyond that, so the baseline 3 is appropriate for a trivially self-documenting enum.

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 precise verb and resource: it reports, per warehouse engine, which cost signals are exact versus approximate. That purpose is clearly distinct from the cost-estimation and bounded-execution siblings, so an agent can tell what this tool produces without opening the 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 prescribes sequencing ('Call this before estimate_query_cost or run_query_bounded') and names both alternatives by name, plus the reason to call it (interpreting accuracy_tier). This is the strongest form of when-to-use guidance.

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