query_history_compare_start

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

Annotations supply readOnlyHint=true and openWorldHint=false, and running COUNT(*) queries is consistent with that read-only profile. The description adds useful behavior the annotations don't cover: the alternating execution and the ``runs`` repetition count, and the polling requirement implies an asynchronous job. It stops short of disclosing whether the runs happen server-side, expected runtime, or timeout behavior.

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 tight sentences with no filler, front-loading the core action before the follow-up poll instruction. The backtick around runs adds a small readability hiccup but otherwise the structure is efficient and well-ordered.

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 5-parameter async comparison tool with no output schema and only minimal annotations, the description covers the start-and-poll lifecycle adequately but leaves the required `shapes` parameter and timeout semantics unexplained. An agent can launch the job but must guess at the meaning of a required argument.

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% across 5 parameters, so the description carries the full burden and only partially delivers. It references ``runs`` explicitly and implicitly maps 'original and the new table' to table/new_table, but says nothing about the required `shapes` parameter or `timeout_s`, leaving two parameters completely undocumented in both schema and prose.

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 (Run) and resource (the selected candidate queries against the original and new table), plus the mechanical detail that queries are wrapped in COUNT(*). It distinguishes itself from siblings like query_history_compare_candidates and query_history_compare_status by naming the run-then-poll workflow. Lacks an explicit statement of the end goal (performance/correctness comparison), which keeps it from a 5.

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?

The phrase 'Poll query_history_compare_status' names the required follow-up tool, giving implied workflow guidance. However there is no explicit statement of when to use this versus the other compare_* siblings, nor any precondition (e.g. that candidates must be selected first). Usage is inferable but not spelled out.

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