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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses the cost model ($0.02 from balance, charged only on a successful return), the external data source (live TikTok), a freshness/rate cadence (weekly), an auth dependency (provider token saved on the app's site settings), and a data-integrity guarantee (emails come from the bio, never guessed). These are exactly the operational facts an agent needs before invoking a paid, open-world call, and they are consistent with readOnlyHint=false.

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?

The payload is front-loaded and information-dense, but the prose is one long run-on chain of clauses with nesting parentheses, and the title ('Slideshows working for your buyers') adds little. Nearly every fact earns its place, yet the delivery could be split into short scannable statements without losing content.

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?

This is a complex tool – paid, open-world, returning posts, creators, emails, and generated tracking links – with no output schema, so the description must carry the return shape, and it does. It also covers cost, cadence, and the App Store (ct=sf-shorts-...) versus utm_source=tiktok link distinction, leaving no material gap for correct invocation.

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 coverage is 100% and the schema already says the strings are searches in buyers' words, so the baseline would be 3. The description goes further by capping intent at 6 searches, warning against using the product name, and giving a concrete phrasing example, which materially shapes how the single parameter should be filled.

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 names a specific resource and scope: top TikTok posts from the last 180 days for up to 6 buyer-style searches, ranked slideshows-first, plus the creators behind them and their public emails. This is clearly distinguishable from sibling research tools such as keyword_research, research, and ideas_run, and an agent knows exactly what comes back (plays, likes, saves, slide count, caption, creator follower range, email, tracking link).

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 explicit operating context – run it once a week for the /shipfound:shorts routine (routines/shorts.md) – and precise guidance on how to phrase the searches (buyers' own words, e.g. "coding games for kids", not the product name). It does not name an alternative sibling tool or state when not to use it, so it stops short of full when/when-not routing.

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