sas_fedsql_check

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

Annotations already declare readOnlyHint=true, and the description reinforces this with 'nothing runs', removing any doubt that it is a dry run. It goes beyond the annotations by disclosing the response fields (`warn` and `message`) and the specific failure condition (ORDER BY on expressions) — valuable since no output schema exists. It stops short of describing the full response shape or whether other fields are returned.

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 sentences with no filler, but the structure is convoluted: the core check is buried inside a nested relative clause, and the `warn`/`message` explanation reads as a fragment ('``warn``: it can't...'). The pre-condition is front-loaded but the rest is not easily scannable.

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 one-parameter, no-output-schema tool, the description must explain both input expectations and return semantics. It partially does the latter (`warn`, `message`) but the meaning of `warn=true` versus `warn=false` is ambiguous in the phrasing 'warn: it can't', and the SQL input format is left unstated.

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?

There is one required parameter with 0% schema description coverage, so the description carries the burden. It implies the input is a FedSQL SELECT statement but never states the expected format (full statement vs. fragment, whether non-SELECT statements are accepted, quoting expectations). Partial compensation only.

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?

The description does convey a specific check: whether a SELECT contains a subquery FedSQL would push down via CREATE TABLE (which fails on SingleStore libraries) and whether the editor can run it as a derived table instead. However, the phrasing is dense and jargon-heavy ('push down with the CREATE TABLE'), and it never names a clean verb+resource like 'validate FedSQL'. An agent can infer it is a pre-flight validator but must work to extract that.

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?

'Before a FedSQL run (nothing runs)' gives an implied trigger — call this prior to executing FedSQL. There is no explicit exclusion, no mention of when to skip it, and no reference to plausible alternatives such as sql_editor_classify, workload_test_statement, or sas_query. Usage is implied rather than stated.

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