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

Annotations already declare idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description nonetheless adds non-obvious behavior: re-saving is safe, and a supplied note replaces the existing note only when provided; it stops short of describing failure modes or ownership requirements for collectionId.

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 tightly packed sentences with no filler; the core action is front-loaded and the caveats (idempotency, note replacement, usage restriction) follow in priority order.

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 four-parameter mutation with rich annotations and no output schema, the description covers the quirks an agent most needs: idempotency, conditional note overwrite, and where collectionId comes from. What a successful save returns, and what happens when the ad or collection is invalid, is left implicit.

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 compensate. It usefully explains collectionId's origin (from list_saved_ads) and note's overwrite semantics, but leaves platform's enum values and the meaning/constraints of id entirely to the bare schema.

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 with scope: 'Save one library ad to the caller's saved ads', plus the optional collection and note effects. It references list_saved_ads as the source of collectionId, but does not explicitly contrast itself with search_ads or other siblings that also surface ads.

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 only when the user asks to save' is an explicit inclusion/exclusion rule, which is strong guidance for a mutation tool. It does not name an alternative for the adjacent cases (e.g., browsing or comparing ads), so the routing is clear but not fully complete.

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