Social Data API

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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the bar is lower. The description adds context not present in structured data: the call is free and costs 0 credits, which materially affects an agent's willingness to call it preemptively, plus it previews the returned trial-state fields.

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?

Two sentences, both front-loaded: what is returned first, then the decision rule and the zero-cost fact. Nothing is repeated from the title or the annotations.

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 zero-parameter, read-only utility with no output schema, the description supplies everything needed: the returned fields, the cost, and the recommended moment to call it. No structural gaps remain.

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?

The tool takes no parameters, so the schema-coverage baseline of 4 applies and no parameter explanation is needed. The description correctly spends no words on arguments and instead focuses on what the call yields.

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?

"Check this API key's plan, credits remaining and trial status" names a specific verb and resource and enumerates the exact fields returned, including trial end date, days left, and whether the trial has started. It is unmistakably distinct from the sibling TikTok/X data-fetching tools.

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 it before a batch of calls if you are unsure what the key has left" gives an explicit trigger condition tied to a concrete decision. It stops short of stating when not to call it or naming an alternative for related questions, but for a zero-parameter utility that gap is minor.

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

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower, and the description adds genuinely new operational context: a cost of 1 credit and a one-profile-per-call scope. It stops short of describing failure behavior for unknown users or any rate limiting, which keeps it out of the top band.

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?

Two short sentences with zero filler: the return contents are front-loaded and the cost/scope constraint follows. Every clause carries information an agent would otherwise have to guess.

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 no output schema, the description usefully compensates by listing what comes back, and it discloses the credit cost. The remaining gap is that it does not mention the anyOf identifier requirement (uniqueId or secUid) or what happens when a profile is not found, though the schema enforces the identifier constraint itself.

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 100% and both parameters (secUid, uniqueId) are documented in the schema itself, including the 'no @' formatting and reuse-from-previous-call hint. The description adds no parameter-level meaning, so the baseline of 3 applies.

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?

Specific verb ('Get') plus a precisely scoped resource ('a TikTok creator's public profile'), followed by an enumeration of the returned fields (followers, following, likes, bio, avatar, verified). This clearly separates it from tiktok_search, tiktok_videos, and the x_profile sibling, which covers a different platform.

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?

'One call returns one profile' implies a single-entity lookup and implicitly warns against expecting bulk results, but there is no explicit when-to-use or when-not-to-use statement, and no routing to siblings such as tiktok_search for discovery. Usage is inferable rather than stated.

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

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. On top of that, the description discloses the credit cost (1 credit) and the shape of the return payload (views, likes, comments, shares, author, caption, hashtags), which are real behavioral facts not present in structured fields.

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 sentences, all front-loaded: purpose first, then result size and returned fields, then cost. Nothing redundant and nothing buried.

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 read-only search with no output schema, the description gives the agent enough to call it correctly: page size limits, payload contents, and cost. The only meaningful gap is the unexplained sort_type enum, which is the one thing a caller could get wrong.

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%, so baseline is 3. The description reinforces the count ceiling ('up to 50 with count') and the default of 20, but adds nothing about offset pagination or what sort_type values 0/1/2 actually mean — the least self-explanatory parameter goes unexplained.

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?

States a specific verb and resource ('Search TikTok videos by keyword'), which clearly separates it from tiktok_videos (listing a known user's videos) and tiktok_comments. It stops short of explicitly naming a sibling to prefer in an alternative case, so it is clear but not fully differentiated.

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?

The keyword-based framing implies the use case (find videos on a topic rather than fetch a known account's content), but there is no explicit when-to-use/when-not guidance and no mention of alternatives such as tiktok_videos or x_search. The agent must infer the routing.

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

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the description is free to add value elsewhere and does: it discloses page-size limits (20 default, 50 with count) and per-call credit cost, including the extra credit charged for the username lookup. It does not explain pagination behavior or whether cursors expire, which keeps it short of a 5.

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?

Two sentences, front-loaded with the primary action and ordering, followed by the two facts an agent most needs before calling: result cap and credit cost. No redundant restatement of the title or schema.

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 simple read-only list tool with full schema coverage and no output schema, the description covers ordering, page size, identifier choice, and cost. It stops short of saying what a returned video record contains, which would matter slightly given the absence of an output schema.

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%, so the schema already documents count, cursor, secUid, and uniqueId. The description only restates the credit differential that the schema also carries, adding no new syntax or format detail; baseline 3 applies.

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?

"List a TikTok creator's videos, newest first" gives a specific verb, resource, and ordering, which distinguishes it from tiktok_comments and tiktok_profile by resource type. It never names tiktok_search as the boundary case, so an agent wanting video content still has to infer which of the two list-like tools to pick.

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?

Usage is implied by the requirement of either a username or secUid, and the credit-cost sentence effectively guides the choice between the two identifier paths. There is no explicit when-to-use/when-not guidance against siblings such as tiktok_search or tiktok_profile.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description adds genuinely new operational facts: 1 credit per call, one profile per call, and a hard plan-gating rule that produces an error for trial keys. That billing and access information is exactly the kind of context annotations cannot express.

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 sentences, front-loaded with the core action and return fields, then cost, then access restriction. Every sentence carries distinct information with no redundancy.

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 no output schema, the description compensates by enumerating the returned fields, and it also states cardinality (one call, one profile), cost, and plan gating. For a two-parameter read tool, an agent has everything needed to decide and invoke correctly.

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 both parameters (username, user_id) are already documented with format examples in the schema. The description adds no meaning about the anyOf either/or requirement or when to prefer user_id over username, so it stays at the baseline for a fully-documented two-parameter schema.

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 opens with a specific verb and resource ("Get an X (Twitter) user's public profile") and immediately enumerates the returned fields (followers, following, bio, verified status). It also implicitly distinguishes itself from the tiktok_profile sibling by naming the platform scope and noting the trial tier is TikTok-only.

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 clear eligibility condition for use: paid plans and pay-as-you-go only, with trial keys receiving an error. It does not, however, route the agent between x_profile and x_search (e.g., search by keyword vs. fetch a known handle), so alternative selection is left to inference.

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