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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), so the agent knows this mutates state reversibly and safely. The description adds only that findings can be marked on a run; it does not mention permissions, auth requirements, or the effect on already-counted 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?

One front-loaded sentence with the action first and the lookup context tucked into parentheses; nothing is wasted, though the guidance to find keys is somewhat compressed.

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 3-parameter mutation tool with no output schema and solid annotations, the description covers the action, the key source, and the optional run scoping. Missing only an explicit relationship to the inverse ignore_finding 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?

Schema coverage is 100%, so the schema documents key, runId, and checkId. The description reinforces where key comes from (get_check) and that runId applies "right away," adding slight meaning, but not enough to exceed the baseline when the schema already does the work.

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?

"Make an ignored finding count again" states a clear verb and resource, and the parenthetical clarifies the domain (monitor findings with keys). It is easily distinguished from the inverse sibling ignore_finding, though it never names that sibling 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?

The parenthetical routes the agent to get_check for retrieving ignored finding keys and get_run for run-scoped marking, which is genuinely useful context. However, it never states when to use this versus ignore_finding or dismiss_recommendation, so the when-to-use guidance remains implied.

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