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

Annotations already declare destructive=true and idempotent=true, so the safety profile is known; the description adds genuinely new behavioral context by revealing that omitting confirmApply degrades the call to a preview. It does not cover reversibility, whether previously restricted seats are overwritten, or what happens on an expectedUpdatedAt mismatch, which matters for a destructive write.

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?

Three short lines: action, when-to-use with the preview caveat, then a concrete example. The behavioral caveat is front-loaded immediately after the when-to-use line, so the most consequential fact is not buried.

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 7-parameter destructive mutation with no output schema, the description covers purpose, trigger, preview semantics, and a full example payload, with parameter provenance left to the schema. The remaining gap is optimistic-concurrency behavior on a stale expectedUpdatedAt—an agent cannot tell whether a conflict errors or is silently ignored.

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 baseline is 3; the worked example adds real value by showing the shape of configurationId, the composite "row:index" seat id format, and that expectedUpdatedAt is a millisecond epoch from get_chart. It reinforces rather than duplicates the schema, though it doesn't clarify version versus expectedUpdatedAt interaction.

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 clear verb and outcome: marking seats flagged by score_sightlines as "restricted view" for buyers. This distinguishes it from the upstream sibling score_sightlines, which only flags them. Slightly awkward phrasing ("Mark seats score_sightlines flags") adds a small parsing cost but the intent is unambiguous.

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?

"Use when: the user accepts the result" gives an explicit trigger condition, and the preview/apply distinction via confirmApply tells the agent when the call is safe versus committing. It stops just short of naming sibling alternatives (e.g., running score_sightlines first, or using update_seats directly).

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