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

Annotations already declare non-read-only, destructive, open-world, non-idempotent. The description adds genuinely new behavior: an owner-approval gate, requestId reuse for confirmation and recovery, and the condition that the feed is only 'live' once status is active. It omits what exactly is destructive (spending implications of the feed schedule) beyond the terse 'Spending/deletion' phrase.

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 clauses: purpose, safety workflow, state claim, plus a documentation pointer. Front-loaded with the operation and no filler sentences.

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 10-parameter, nested-object, destructive mutation with no output schema, the description covers the approval/confirmation loop and outcome-recovery hint but not the feed schedule structure, required catalog linkage, or what a successful response/status looks like. Adequate but with clear gaps an agent would hit on first call.

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 60%, and the description reinforces the two most consequential parameters (confirm and requestId) with approval/reuse semantics. It says nothing about the nested payload (name, schedule interval/url/hour/dayOfWeek) or the accountId vs adAccountId vs parameters.catalogId distinction, leaving the remaining 40% of undocumented params unaddressed.

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 description states a specific verb and resource ('Create a product feed') and scopes it to Soclo Ads, so an agent can distinguish it from reads like list_ad_catalog_feeds. It does not, however, explicitly distinguish it from the very close sibling soclo_ads_create_ad_catalog_feed_upload, which an agent would need to disambiguate between.

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?

It gives a procedural path (preview first, then owner-approved confirm:true with the same requestId) which implies when confirmation is appropriate. But it never names the preview/quote sibling to call first, nor when to choose this over the feed-upload variant, so the routing guidance is only implied.

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