DouParse - Short Video Link Parser

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

With no annotations, the description must carry the full behavioral load. It implicitly signals a read-only quota inspection by listing only observational fields (remaining count, rate limit, today's usage, status), which is helpful, but it never states that the call has no side effects, whether it consumes quota, or what auth or key scope is required.

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 sentence, front-loaded with the verb, that lists the returned data points without padding or repetition. Every element earns its place and nothing is wasted.

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?

The tool is simple: no parameters and an output schema that already documents the return shape, so the description need not explain return values. It is nearly complete, with only the implicit auth context and side-effect profile left unstated.

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 zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool applies. The description adds value by naming the implicit 'current API Key' subject that the empty schema cannot express.

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 states a specific verb (查询) applied to a specific resource (the current API Key's quota) and enumerates exactly what is returned: remaining calls, per-minute rate limit, today's usage, and status. It does not explicitly name the siblings, but parse_video and redeem_code are unrelated domains, so the distinction is obvious from the resource alone.

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?

Phrasing like '当前 API Key' implies that the tool reads the caller's own quota, and the field list implies a pre-flight check before heavy usage. However, there is no explicit statement of when to call it, no prerequisites, and no guidance on alternatives or frequency of use.

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?

With no annotations, the description carries the full burden and does substantial work: it discloses that links are unwatermarked, resolve to platform CDN addresses the caller must fetch itself, and are time-limited so an expired link requires re-parsing. It does not mention authentication requirements, rate limits, or what happens for unsupported/private content, 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?

Front-loaded: the core action and return type appear in the opening line, followed by platform coverage, input forms, and output field hints in that order. The trailing Args block largely restates the url sentence already given above, which is the only wasted text.

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 one-parameter extraction tool with an output schema present, the description covers platform scope, all three input forms, which return fields matter for video vs. image-set vs. music, and the download/expiry caveat. Failure modes such as unsupported platforms or private/deleted content are not addressed, which is the remaining gap.

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% and the single url parameter has no schema description, so the description must compensate — and it does, explaining that url may be raw share text, a short link, or a complete link, with a concrete example format. It adds real meaning over the bare {"type": "string"} schema, though it stops short of stating tolerance for extra whitespace or invalid input.

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 first line names a specific verb and resource (解析分享链接) plus the concrete outcome (返回无水印直链), and the platform list immediately frames the scope. Against siblings get_balance and redeem_code there is no ambiguity whatsoever.

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 spells out the accepted input shapes — share text containing a token, a short link like https://v.douyin.com/xxx/, or a full URL — which is exactly the decision an agent faces before calling. It also tells the caller what to do afterwards (download the CDN link yourself, re-parse if it expires). No explicit when-not-to-use case or alternative tool is given, but the siblings are unrelated, so nothing is really missing.

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?

No annotations are supplied, so the description carries the full burden. It does disclose the critical irreversible trait that the code is consumed (一码一用), which is valuable. However, it says nothing about which account receives the credits (presumably the authenticated caller), required auth, error behavior for invalid/expired/already-used codes, or idempotency — significant gaps for a mutation tool with zero annotation coverage.

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 core sentence is front-loaded and the single-use constraint is placed exactly where it matters. The Args block slightly restates the parameter but adds the provenance detail, so it earns its place; nothing is bloated.

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?

An output schema exists, so return values need not be explained, and the tool is simple (one required string). Still, for a credit-granting mutation with no annotations, the description omits the target account and failure modes, leaving the agent under-informed about what happens on an invalid or spent code.

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 0% and the schema only names the field 'code' with a generic 'Code' title, so the description must compensate. It does add meaning by identifying the code's source (backend / card-issuing platform), which helps the agent know where such a value originates. It stops short of describing format or validity constraints.

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 states a specific verb+resource with a concrete effect: redeem a code to add call quota to the account. The parenthetical '(一码一用)' adds the key semantic that each code is single-use. It is clearly distinct from siblings get_balance (read balance) and parse_video, though the distinctness is implicit rather than stated.

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 only implied: call it when you have a redemption code in hand. There is no explicit guidance on when NOT to use it, no pointer to get_balance for verifying the result, and no mention of what to do if the code was already redeemed or is invalid.

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