Scrape Substack publications, posts, and search

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

Goes well beyond the read-only annotations: it discloses that an APIFY_TOKEN is required, that Apify bills per post row and per publication row, that invalid input returns a free row whose error_reason starts with input_invalid:, and that a failed run is returned as an error with its run ID. These are exactly the operational facts an agent needs before invoking.

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 the two modes, then details outputs, then error/cost behavior—a sensible ordering. It is dense and somewhat run-on with many clauses in one paragraph, but nearly every sentence carries operational value.

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 10 parameters, no required fields, and no output schema, the description does the heavy lifting on return shape: it enumerates publication row fields and post row fields, and covers error and billing semantics. It omits how optional controls like include_body or since_days change the returned rows, a minor but real 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 already 100%, so the schema carries the parameter burden. The description restates the accepted publication formats and the search_output behavior, which is useful reinforcement but adds little new meaning, and it never mentions include_body, since_days, proxy_mode, or max_charge_usd. Baseline 3 is appropriate.

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 specific verbs and resources: reading Substack publications and posts, and searching Substack by keyword. It clearly separates the two operating modes (listed publications vs. keyword search) so an agent knows exactly what the tool does without opening the 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?

Explains that input is publications or search queries and that search_output controls whether search returns posts or publications, which effectively tells the agent which input to supply for which goal. There are no sibling tools to disambiguate against and no explicit 'when not to use' guidance, so it stops short of a 5.

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