sas_singlestore_log

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

Goes well beyond the readOnlyHint annotation: it discloses that MV_PLANCACHE stores totals per plan, so rows and milliseconds are per-run averages, that literals are masked as '^', and that an identical statement from another session in the same seconds would also appear. These are exactly the caveats an agent needs to avoid over-reading the results.

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?

Three sentences, front-loaded with the identity of the tool, followed by data-source provenance and then caveats in priority order. Parenthetical lists add bulk but every clause conveys real information; the run-on structure is the only cost.

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?

With no output schema, the description still hints at the returned fields ('rows and ms') and the source table, and it flags the aggregation and masking behavior that governs how results must be interpreted. A fuller return-column list would be needed for a 5, but nothing essential for correct invocation 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 coverage is 0% and both parameters are bare numbers, so the description must carry the meaning — and it does, stating that started_at and ended_at are epoch seconds bounding the run. It stops short of specifying boundary inclusivity or whether the window is a single run or an arbitrary range, so it does not fully compensate.

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 resource and scope: the SingleStore-side statements behind a SAS run, queried from MV_PLANCACHE over an epoch-second window. The framing 'The SingleStore side of a SAS run' implicitly separates it from the SAS-side siblings (sas_query, sas_rows, sas_execute), but no sibling is named explicitly.

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?

Usage is only implied: you call it with a run's started_at/ended_at to see what the cluster actually executed. There is no explicit when-to-use statement and no routing to alternatives such as query_history or sas_history_lookup for the same diagnostic goal.

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