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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds non-obvious behavior — pack settings are re-validated and the landing type is immutable — but it never addresses what makes this destructive or what happens to fields left out of a partial update.

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 dense sentence with the core edit semantics first and the field-constraint clauses after. No filler, and every clause carries a rule an agent would otherwise get wrong.

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 an 18-parameter partial-update tool with no output schema, the description covers the highest-risk ambiguities (type immutability, cross-type field validity, settings re-validation). Remaining gaps are minor: no statement on return value or on error behavior when a game field is sent to a URL landing.

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?

With 18 parameters, 61% coverage and nested objects, the schema leaves conditional logic unstated; the description supplies exactly that by partitioning url vs. game-only fields and flagging re-validation against the pack. It does not cover tags, status, group_id, language, collect_push or the protect_* interaction with URL landings.

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?

"Edit a landing (partial)" names a specific verb and resource and immediately signals partial-update semantics, which distinguishes it from create_landing. It also states an invariant ("the type never changes"), but it never names the read/creation siblings it is adjacent to.

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?

Gives conditional applicability rules: url only on URL-type landings, game fields only on game landings, type immutable. That is real when-to-use guidance for each field group, though it says nothing about when to prefer update_landing over create_landing or get_landing.

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