Search Substack

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

Annotations already declare readOnly, openWorld, idempotent and non-destructive, so the bar is lower. The description still adds real value: result partitioning into people/posts/Notes, the caveat that later pages may hold only posts and Notes, and the fact it mirrors the live search box (implying variable, non-exhaustive results).

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 purpose, then chaining guidance, then pagination caveat. No filler and nothing repeated from 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?

There is no output schema, so the description carries the return-shape burden and does: it says results come back split into people, posts and Notes, that IDs are reusable in specific write tools, and how to paginate. An agent has everything needed to call and consume it.

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 would be 3; the description earns above that by explaining the paging model ('Page with next_cursor; later pages may hold only posts and Notes'), which tells the agent what the cursor parameter actually does and why page 2+ looks different.

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 all of Substack for people, posts and Notes') and clarifies the scope is the whole platform, not the user's feed or subscriptions. This distinguishes it from siblings like get_feed, list_posts and list_subscriptions without needing 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?

Explicitly explains how it behaves ('runs Substack's search as the search box does') and gives concrete downstream chaining with follow_user, like_post, reply_to_note, send_message and recommend_publication. It does not name a when-not-to-use case or contrast with get_feed/list_posts for browsing, which keeps it from a 5.

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