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

Annotations cover the basic safety profile (a non-destructive write with openWorldHint=false), but the description adds real context the agent cannot derive: the org-admin permission gate, the cross-organization validation rule, and the approval-path caveat. It is silent on a key behavior: whether orderedIds must be exhaustive or whether unlisted columns retain their current position. Also, 'set display order' reads as an absolute, repeatable operation even though idempotentHint=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?

It leads with the core action, then adds constraints in descending order of importance, with no repetition. The approval sentence is somewhat generic policy boilerplate, but it still earns a place because it warns of an external gate.

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 and annotations exist, so the description need not explain return values. However, an ordering tool with a single nested array parameter leaves the most consequential question unanswered: what happens to columns left out of orderedIds. That gap matters for a tool that rewrites display state across an entire organization.

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%, so the description must carry the burden, and it does only partly. 'Display order' and 'all selected columns must belong to this organization' imply that orderedIds is an array of column UUIDs and that the list may be a subset. It never mentions the 1-100 item bounds or that the array index defines the new position.

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 first sentence gives a specific verb and resource: 'Set milestone column display order.' That distinguishes it from list_milestone_column and update_milestone_column by making its job reordering a collection. It never names those siblings, though, so the agent must infer the boundary from the name alone.

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 description supplies two gating conditions, org-admin-only and same-organization membership for the columns. It never states when to pick this tool over update_milestone_column, and it omits prerequisites such as whether the column set must already exist.

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