LinkDigest — Xiaohongshu, Douyin, TikTok, YouTube to text

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

Annotations already establish readOnly, idempotent, non-destructive, non-open-world behavior, so the bar is lower. The description adds non-obvious behavior the annotations cannot convey: it works without a key and then returns pricing plus key-acquisition instructions, and it discloses the Alipay payment path.

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-loads what is returned, then appends the no-key behavior and the invocation timing. Two sentences with little waste, though the payment-method and sign-in details are slightly dense parenthetical material.

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 and no parameters, the description carries the return-value burden and does so adequately: credits remaining, per-read pricing, purchase links, and no-key fallback. Good enough for an agent to call and interpret it, though it does not sketch the response shape.

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 there is nothing for the description to disambiguate; the 0-param baseline applies. The description correctly focuses on output instead of inventing input semantics.

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 precise resource and what it reports: remaining credits for the API key, per-read costs, and purchase links. The reference to digest_url makes it clearly distinguishable from its only sibling without opening either schema.

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?

Gives explicit trigger conditions — call before a batch of reads, or after digest_url reports exhausted credits. Covers when to use it well, though it does not state any case in which it should be skipped.

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?

Beyond the annotations (readOnly, openWorld, non-idempotent, non-destructive), the description discloses the things an agent most needs: an API key is required, the first call is not the final result (batch id + collect pattern), and each link is billed at its usual price with cached links free and the comparison at 1 credit per 10 links. The schema also warns that re-sending urls restarts the batch, consistent with idempotentHint=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?

Front-loaded with the core action and output contents, then workflow, then cost, then example — a sensible order. It is dense with parenthetical bilingual labels and pricing details that make it longer than strictly needed, but nearly every clause carries information an agent needs.

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?

No output schema exists, and the description compensates by describing what the comparison contains and that the first call returns a batch id. Auth, cost, and the async collect pattern are all covered, so an agent can invoke and follow up correctly without further information.

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 baseline is 3, but the description adds value the schema lacks: a concrete urls example, the batch_id-driven collect pattern, and the credit cost of insight/breakdown/translate_to (+1 per link each). It stops short of explaining the exact comparison output shape for each flag.

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 (read as one batch, write one comparison) over a specific resource (a set of links from named platforms), and enumerates what the output contains: shared themes, hooks, formats, claims, objections, gaps, with every example attributed to a source link. This is clearly distinguishable from digest_url (one link) and search_links (find links).

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?

Gives concrete when-to-use context (after the browser extension's 'Digest the notes on this page' button, call list_batches and pass the newest batch_id here) and explains the two-call lifecycle: first call starts the batch and returns a batch id, later calls collect with batch_id. It does not explicitly contrast with digest_url for the single-link case, so the exclusion is only implicit.

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?

Beyond the annotations (readOnly/openWorld/idempotent=false) the description discloses credit costs, free-tier rate limits, auth requirements, the resume-via-job_id behavior that explains the non-idempotent hint, and the partial_ok refusal-vs-partial tradeoff. This is exactly the context annotations cannot carry.

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 with purpose, then platforms, then output, then constraints and example — good ordering. It is dense but nearly every clause carries operational information; the parenthetical pricing details slightly bloat the middle.

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?

No output schema exists, yet the description enumerates the return shape (transcript, key_point_support, coverage, answer/found, links) and explains the job_id polling path. For a 9-parameter tool with all params documented, nothing an agent needs to call it correctly is missing.

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 baseline is 3; the description still adds cross-parameter meaning: url is mutually exclusive with job_id, and re-sending the url restarts the job. It also gives a concrete url/ask example and the depth caveat that YouTube is always read in full.

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 ('Read what a social media link actually says') and enumerates the supported platforms plus the exact artifacts returned (transcript with times, on-screen text, image text, key points with quotes, coverage receipt). An agent can tell this apart from search_links/compare_links without opening any schema.

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?

Explicitly lists supported and unsupported platforms (Facebook and Spotify not supported), states the no-key trial limit ('two a day per address'), points to check_balance for full output, and gives the polling rule for job_id. Alternatives and exclusions are named rather than inferred.

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?

Goes well beyond the annotations (which already cover readOnly/idempotent/non-destructive/closed-world) by disclosing ordering (newest first), that it consumes no credits and starts no work, and that an API key is required. It also enumerates the exact per-line output fields, which is the main behavioral unknown in a tool with no output schema.

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?

Purpose and scope are front-loaded, and the output-line enumeration earns its space given there is no output schema. The dense opening sentence with em-dashes is slightly heavy but carries real information, not 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 no output schema, the description carries the return-format burden and does so completely: field list per line plus the possible synthesis states. Combined with the cost/side-effect statement and the compare_links handoff, an agent has everything needed to call and consume this tool.

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%, so both parameters (label, limit) are already documented in the schema with their bounds and defaults. The description adds no format or semantic detail for these parameters beyond the schema, so 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?

States a specific verb and resource (list the last batches), plus scope and ordering ('on this API key, newest first'). It also names the origin of unusual batches (browser extension digest on Xiaohongshu/Douyin tabs), which is exactly the kind of distinction that separates it from siblings like search_links and compare_links.

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?

Explicitly routes the agent onward — 'Pass a batch_id to compare_links to read the comparison' — and reassures about cost/side effects ('Starts nothing, costs nothing'). It does not, however, state when to prefer or avoid this tool versus search_links or check_balance, so it stops short of full alternative coverage.

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?

Goes well beyond the readOnly/openWorld/idempotent annotations by disclosing the credit cost model per platform, that 'nothing found is free', metered-by-credits rather than hourly limits, and that an API key is required. Also explains the no-login public-page read path for xiaohongshu and the embed-player read for douyin. Slightly dense but covers the traits an agent needs.

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 with purpose, then cost, then per-platform behavior and an example — a sensible order. It is longer than typical and the platform-specific details run together, but nearly every sentence carries actionable information.

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?

Covers purpose, cost, auth, platform-specific limitations, the digest→compare_links workflow, and a worked example, which is everything needed to call a metered search tool with no output schema. No material 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?

Schema coverage is 100%, so the baseline is 3; the description adds workflow-level meaning by tying digest: true to the compare_links follow-up via batch_id, and gives a concrete example query/platform/limit set. It does not explain insight/breakdown, but the schema already documents those.

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?

Opens with a specific verb+resource ('Find posts on a topic') and immediately enumerates the five platforms searched, so an agent knows exactly what this returns without opening the schema. It is clearly distinct from siblings like digest_url (reads a single link) and compare_links (compares a batch).

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?

States explicit routing: pass digest: true to read results as one batch and then use compare_links with the batch_id. It also gives a concrete alternative path when xiaohongshu lacks web-indexed coverage (extension button, then list_batches), and notes douyin's Chinese-language query effectiveness.

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