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

Annotations cover the safety profile (readOnly, non-destructive, openWorld), and the description goes well beyond: it discloses the auth requirement (APIFY_TOKEN), the billing model (charged per change row and per site check that is first or finds a change; unchanged sites free), the returned row shapes (site_baseline vs site_check plus per-change rows), error behavior with run ID, and that unreadable sites still return a priced-free row_status. This is exactly the extra context a read-only-but-billed tool 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-loads the core purpose and the state_key contract, then layers mechanism, output shape, and cost. It is a dense single paragraph, slightly long, but nearly every sentence carries distinct information; little is redundant 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 14 parameters, no output schema, and a non-idempotent, chargeable behavior, the description supplies the missing pieces: return-row structure, first-check vs subsequent-check semantics, free-vs-billed cases, and failure signaling. An agent has enough to call it correctly without guessing.

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 the schema already documents every parameter in depth (examples, limits, defaults, enum meanings). The description largely restates that ground (domains vs URLs, Shopify/WooCommerce feed vs SaaS pages, per-change billing) without adding syntax or format detail beyond the schema, so the 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 a specific verb+resource ('Watch competitor stores and SaaS sites and return only what changed'), with scope nailed down (price, compare at price, stock per variant, new/removed products, plans, changelog). The 'only what changed since the last run with the same state_key' phrasing pins the tool's contract precisely. No siblings exist, but the definition is self-sufficiently specific.

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 strong operational context: what to pass as sites (domains or URLs, with examples), what state_key does across runs, and that unreadable sites come back free rather than failing. It does not state explicit exclusions or alternatives, but there are no siblings to route against, so the context is effectively complete.

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