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

Annotations already declare readOnlyHint=false, openWorldHint=true, destructiveHint=false, and the title 'Research competitor ads'. The description adds genuinely new behavior — that the call costs AWT and is bounded by a spend cap — which is valuable beyond annotations. It still leaves out what happens on insufficient AWT, whether results persist, and how wait_seconds/idempotency behave.

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 terse clause for an 18-parameter tool with a five-value mode enum is under-specified rather than concise. There is no wasted text, but there is far too little front-loaded information for the tool's complexity.

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?

High complexity, 18 params, a nested object, no output schema, and zero schema descriptions mean the description is the only documentation — and it covers only platforms and an AWT cap. An agent would have to guess at the kind-dependent parameter requirements.

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% across 18 parameters including a nested ad_hoc object, so the description must compensate and barely does. It implies 'platforms' and the AWT cap (confirm_spend_awt), but says nothing about kind's five modes, competitors/ads UUIDs, date_from/date_to, limit_per_advertiser, retry_of, or save_results.

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 verb+resource ('scan ... ad libraries') is identifiable, and four platforms are named, but the description omits that this is a multi-purpose endpoint covering five 'kind' values (scan_competitors, ad_hoc_search, transcripts, media_analysis, retry). The leading fragment 'Competitor intel: quote, then scan' is cryptic jargon rather than a clean statement of what the call does.

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?

'quote, then scan' hints at a two-phase spend-approval flow, which is some sequencing guidance, but nothing explains what 'quote' means, when to use this versus competitor_scans_list, competitor_ads_list, or research_deep, or when a scan should not be started. An agent cannot determine prerequisites from this.

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