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

Annotations already declare this is a non-read-only, non-destructive write (readOnlyHint=false, destructiveHint=false). The description adds important beyond-annotation context: it's a 'write scope — ask the user first' operation and that the mark persists across scans. It doesn't cover rate limits or confirmation mechanics beyond the 'ask first' note, so 4 rather than 5.

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 sentences, front-loaded with the core effect and the write-scope warning, followed by examples and the undo pointer. No wasted text.

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 simple 3-parameter write tool with full schema coverage and annotations, everything an agent needs is present: the effect, persistence, examples, and the undo path. No output schema exists, but return values aren't needed to call it correctly.

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 each parameter (reason, issue_id, project_id) is already documented in the schema, including that issue_id comes from list_issues/get_issue. The description adds no parameter-level detail beyond that baseline, so 3 is appropriate.

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 states a specific verb (mark) and resource (issue thread) plus the exact effect: it stops counting against the score and persists across scans. This is clearly distinguished from the sibling `unacknowledge_issue`, which is named as the inverse operation.

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?

It gives concrete when-to-use examples (noindex on pagination, deliberately short page, required redirect) and explicitly names the reverse tool for undo. This is exactly the when/when-not/alternatives guidance an agent needs.

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