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

Annotations declare readOnlyHint=false and destructiveHint=false but say nothing about the approval workflow. The description adds real value beyond them: no change is applied, approval happens manually in the SKU.io UI at a named location, and the call returns a set id, status and link. It omits idempotency behaviour despite an idempotency_key parameter, which keeps it from a 5.

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 sentences with no filler. The scope and the proposal-only nature are front-loaded before the return-value note, so the most decision-relevant facts come first.

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 six-parameter tool with a nested changes array and no output schema, the description covers what it does, that nothing is applied, and what comes back (set id, status, link). The gaps are the unmentioned optional parameters (dry_run, summary, idempotency_key), which an agent would have to discover from the schema alone.

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 50%, so the schema documents some parameters (reason, dry_run, idempotency_key, after, entity_type) while ad_account_id, summary and the changes array structure are undocumented. The description partially compensates by naming the four change kinds, which map onto the operation enum, but it never explains dry_run, summary, reason or the idempotency key, so the baseline 3 is appropriate.

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 ('Proposes'), enumerates the exact change classes (bid, budget, pause/enable, ad-rate) and scopes it to 'one ad account'. An agent can immediately distinguish this mutation-proposal tool from the read/explain siblings such as explain_ad_change, get_ad_recommendations or get_ad_performance.

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 sentence 'Nothing is applied: a person approves them in SKU.io under Advertising → Changes' gives the key usage context: this is a proposal-only path that requires human approval downstream. It does not explicitly name alternatives or state when-not to use it (e.g. when a change is already approved or when only explanation is wanted), so it falls short of a 5.

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