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

Annotations already declare the mutation is non-destructive and idempotent, so the bar is lower. The description adds real value by naming expectedVersion and idempotencyKey, implying optimistic-concurrency failure modes and retry safety, but it never says what a version conflict looks like or what state 'reviewed' transitions the action into.

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 compact sentences, front-loaded with the core action and immediately followed by the scope constraint. Nothing is wasted, though the phrasing is dense enough that the identifiers are mentioned without explanation.

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 mutation tool with no output schema, the description covers the safety profile reasonably and rules out adjacent jobs, but leaves the three undocumented parameters and the post-call state ambiguous. An agent can invoke it without erroring, but cannot confidently construct reason/workspace values.

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 must compensate and it only touches two: expectedVersion and idempotencyKey, without explaining the sha256-hex format or the retry contract. actionId, reason, and workspace are entirely undocumented anywhere — an agent must guess that reason is optional free text and workspace is a scoping selector.

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 gives a specific verb and resource — 'Mark a suggestion reviewed' — and then scopes it with 'Task triage only, not copy approval, generation, publication or outcome verification,' which separates it from siblings like prepare_page_changes or dismiss_preparation_action. It is clear what the tool does, though it never explicitly names which sibling to use for the excluded cases.

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 exclusion list ('not copy approval, generation, publication or outcome verification') is explicit when-not guidance that most definitions lack. What's missing is the positive routing: it does not name dismiss_preparation_action or read_preparation_action as the alternatives for the cases it disclaims.

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