query_history_compare_cancel

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

The description states the tool stops/cancels running work, which is an action with side effects, yet the annotations declare readOnlyHint=true. That is a direct inconsistency: the agent is told this is a side-effect-free read while the text describes terminating live statements. The extra detail about the in-flight statement being cancelled is useful, but it is precisely what contradicts the annotation.

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?

A single short sentence with the action verb front-loaded and the side effect appended in parentheses. Nothing is wasted and it is easily scanned. It is not padded, though it is arguably too terse to be fully useful rather than 'concise'.

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 state-changing cancel operation with no output schema and no meaningful annotation support, the definition leaves key questions unanswered: what happens to partial comparison results, what the tool returns on success or on an already-terminated job, and whether job_id must reference a live job. The one behavioral detail given (the running statement is also cancelled) is helpful but insufficient for a mutation tool.

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 exactly one parameter, job_id, and schema description coverage is 0% — the schema gives only a type and title. The description makes no attempt to explain what job_id is, where to obtain it (e.g., from query_history_compare_start or query_history_compare_status), or what format it takes. With one undocumented parameter, the description fails to compensate for the schema gap.

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 pairs a specific verb (stop) with a specific resource (a running comparison), and the parenthetical clarifies exactly what gets stopped: the statement running now. An agent can distinguish it from query_history_compare_start and query_history_compare_status without opening a schema. It stops short of naming siblings explicitly, so it is clear but not maximally differentiating.

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 description conveys the implied scenario (a comparison is running and you want to halt it) but offers no explicit 'when to use this vs. alternatives' guidance. It never says whether the job_id comes from query_history_compare_start, whether query_history_compare_status should be checked first, or what happens if the job already finished. No exclusions or prerequisites are stated.

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