Server Quality Checklist

Tool Scores

• map_tiktok_brand_presenceA
  4.4/5.0
  Behavior5/5

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

  The description adds meaningful behavioral disclosures beyond the annotations: TikTok rounds counts above roughly ten thousand and the row flags that; a failed identity check surfaces as identity_mismatch with zero counts rather than silently returning bad data; the escalateOnBlock retry semantic reveals the tool can transition to residential routing. It also names upstream behavior ('TikTok answers most requests over cheap datacenter routing') that contextualizes the blocked status. The 'Read only' claim is consistent with readOnlyHint=true; no contradiction.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  At roughly 105 words, the main description is dense but every clause earns its place: intent, output shape, rounding caveat, identity-failure semantics, and cost warning all load in sequence. It front-loads the core action before edge cases. A half-point off for the CSV-like return field list ('follower, following, like and video counts...') which could be trimmed, but that is minor — structure fidelity is high and the most important behavioral caveat (rounding) comes early.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a mutation-adjacent tool with six parameters, zero required, no output schema, and no siblings, the description covers all the bases: it explains the return payload (counts, verification, bio, link), the two error/edge statuses (identity_mismatch, blocked), the rounding edge case, the read-only safety profile, and the cost implication. With no output schema present, the description's inventory of returned fields is what makes the tool callable without a single round-trip to the API. The only trivia an agent can't know is the exact JSON shape of the row — immaterial when Clay is the sink.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the baseline of 3 applies. The parameter descriptions themselves are exemplary — they explain tone (skipCache serialized as a string for Clay), priming (handle is PRIMARY), and failure modes (blocked on escalation). However, the main description itself adds no parameter-level meaning; it focuses on return shape and error states. No deduction needed, but also no bonus: the description correctly leaves the parameter documentation to the schema where it already exists at full coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a specific verb+resource pairing — "Resolve a TikTok handle, or a company domain, to that brand's official TikTok account" — and immediately enumerates the exact deliverable fields (follower counts, verification status, bio, outbound link). It goes far beyond a restatement of the tool name, and the identity-mismatch sentence further disambiguates what the tool is (an identity-verified resolver, not a fuzzy lookup). Even without sibling tools to distinguish from, nothing about the core purpose is left to inference.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description supplies clear operational context: it is read-only, requires an APIFY_TOKEN, and consumes credits per call. The parameter docs add routing guidance about preferring handle over domain discovery ("only 4 of 14 B2B homepages declare a TikTok link") and when to flip escalateOnBlock or includeFollowerCounts. It lacks an explicit 'use alternative X instead' statement, but with no siblings that exclusion is legally unnecessary; a small deduction for the cost/intent guidance being spread across parameters rather than fronted in the main body.

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