query_market_data

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

With no annotations, the description carries the full disclosure burden and meets very little of it: it never says the operation is read-only, that results are row-limited, or how failures surface. It also calls itself a plain alias while the schema demands an extra required `asset_class`, so the agent cannot tell how much of `query`'s contract actually carries over.

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 and waste-free in themselves, but the brevity is achieved by omitting what matters rather than by compression. Appropriate length for a well-annotated tool, too thin for one with no annotations and partial schema coverage.

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?

No annotations, no output schema, and a schema whose own description is a stale internal design note that describes a one-field payload while the surface requires two. For a bare SQL-execution tool the description needs to cover read-only status, row caps, and available views; it covers none of these.

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 only 50% and the description says nothing about parameters. The `sql` field has no description anywhere, so the only place dialect/scope meaning could be supplied is the description, and it isn't.

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 and resource ("Execute DuckDB SQL against the lake's channel views") and names the sibling it duplicates ("alias of query"), so an agent can locate it relative to `query`. It stops short of 5 because calling it only an alias obscures whether any behavior actually differs.

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?

"alias of query" implies the two are interchangeable but gives no when-to-use / when-not guidance and no prerequisites (e.g. must a channel be collected first?). Nothing tells the agent how to choose between this and `query`, `catalog-scan`, or `search`.

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