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

Beyond the readOnly/openWorld/destructive annotations, the description discloses credit economics ('one credit per search call (platforms × queries, default 3 × 3) plus one per enriched profile; repeats inside 20 minutes are free'), enrichment behavior, and the data-quality guarantee 'Real people, not AI actors'. This gives an agent clear expectations about cost, output contents, and reliability.

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 paragraph is long but information-dense: scanning behavior, ranking criteria, contact data, use cases, credit costs, and follow-up tools are all present. It is front-loaded with the core function before moving to cost and workflow. It could be broken into clearer sentences or bullets, but there is no filler.

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?

With 7 parameters, no output schema, and a paid search tool, the description covers the essentials: output contents ('the top rows get follower counts AND public contact info'), credit cost, and intended workflow. The main completeness gap is the undocumented minAvgViews parameter, which neither the schema nor the description explains clearly, leaving a small but real ambiguity for an agent.

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 high (86%), so the baseline is 3; the description adds value by tying queries and platforms to credit costs and explaining that enrich yields 'follower counts AND public contact info'. It also connects ranking to 'median views, engagement rate and how often they show up,' informing parameters like minAvgViews and minEngagement. One gap remains: minAvgViews has no schema description and the tool description never explains its units, so it does not reach a 5.

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 verb ('Scan organic TikTok, Instagram Reels and YouTube'), a concrete resource (creators matched to a niche), and a clear outcome (ranked creators with followers and public contact info). It also distinguishes itself from raw search or saved-creator siblings by saying 'fold the posts into creators' and 'Real people, not AI actors.'

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 cases are explicit: 'for influencer sourcing, UGC casting and partnership prospecting' and 'who should we send product to?'. It also names follow-up tools like save_to_swipefile, fetch_social_data, generate_text, and manage_meta_partnership_creator, giving an agent the downstream workflow. It stops short of an explicit when-not-to-use warning versus content-search siblings, so it earns a 4 rather than 5.

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