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

Annotations only say this is a non-read-only, open-world, idempotent write; the description adds the material context — it spends workspace balance, request_id makes retries return the same run and never double-charge, needs_confirmation means nothing started, and the call returns a run_id while work continues in the background. The untrusted-content warning is useful, though the trailing two sentences overlap somewhat. It does not state what happens to existing cell values beyond the opt-in overwrite, which the schema covers.

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, idempotency, confirmation, testing, and polling in a logical sequence. It is dense but nearly every sentence carries operational information; the two closing safety sentences are somewhat repetitive boilerplate and could be condensed.

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 14-parameter, nested-object, no-output-schema tool, the description supplies the missing pieces: what is returned (a run_id), how to await completion (get_run with wait_seconds up to 50), cost implications, and the confirmation handshake. An agent has enough to invoke this 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 coverage is 93%, so the baseline is 3, and the description earns an upgrade by explaining cross-parameter behavior the schema cannot: omit provider for auto-routing, force_refresh skips cached pages, test_rows runs a subset with its own run_id, and confirm_token/test_confirm_token drive the confirmation flow. Parameters like subpages, overwrite, only_rows_where, and url_column are left entirely to the schema.

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 and resource: "Fetch the web page (or LinkedIn company page) for each URL in a column and return its text." That immediately separates it from siblings like run_ai, run_verify, and run_flow, and the scope (per-row batch over a list or sheet) is explicit.

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 gives concrete routing rules and alternatives: leave provider omitted and never ask the user which scraper to use, call estimate_cost first for pricing, use output_name for lists vs target.sheet.output_column for sheets, and poll get_run with wait_seconds until the run ends. It also spells out the exact branch to take on a needs_confirmation result.

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