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

The description usefully discloses two things annotations don't: that reason/category feed the AI's future behaviour, and that the call is confirm-gated and previews by default. However, it never states what happens to the run itself (status change, irreversibility, whether it can be re-queued), which matters for a mutation with only readOnlyHint=false.

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 front-loaded sentence with the confirm gating in a parenthetical; nothing is redundant. Slightly dense with two ideas crammed into one clause, but efficient overall.

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 4-parameter mutation with minimal annotations and no output schema, the description covers the gating behaviour and the effect of reason/category but omits the resulting state of the run, reversibility, and the category vocabulary. Adequate but with clear gaps.

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 25% (only confirm is documented), so the description must compensate. It does add meaning for reason and category by explaining they influence the model's future behaviour, but leaves runId entirely implicit and gives no hint of valid category values despite there being no enum.

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 and resource ('Reject an AI-generated plan'), which unambiguously identifies the operation and implicitly contrasts with the sibling approve_ai_run. It does not explicitly name the counterpart, so it stops just short of a 5.

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?

Usage is inferable from the domain (rejecting a run after reviewing it via list_ai_runs_awaiting_review/approve_ai_run), but no when-to-use or when-not guidance is stated. The mention of get_platform_rejection_trends is a downstream reference rather than an alternative-selection hint.

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