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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds real value beyond that by disclosing blast radius: sibling cells continue independently and already-committed applications stay in sheet history, which tells the agent the cancellation is partial and non-retroactive.

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 with the action and scope, then the consequence. No filler and no restatement of the name or title.

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?

An output schema exists, so return values need not be explained, and the description covers the key behavioral risk (partial cancellation, history preserved). The remaining gap is the lack of guidance on when to invoke this versus an undo/restart path, which matters for a destructive mutation.

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 only 33%, so the description must compensate and it only partly does: it clarifies runId semantics (identifies the single run to cancel) but says nothing about sheetId, and it is silent on the required idempotencyKey even though idempotentHint is false.

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 (cancel), a precise resource (one cell run), and the identifier it acts on (run ID). The scope qualifier 'exactly one' cleanly separates it from any batch/worksheet-level cancellation an agent might otherwise assume.

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 implied usage (cancelling an in-flight cell run when its run ID is known) is discernible, but the description names no alternative tools and no when-not condition — e.g. it never says what to do after cancelling or how it relates to sheets_restart_version_restore or undo paths.

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