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

Annotations already declare readOnly/openWorld/non-destructive, but the description adds genuinely new operational facts: per-call cost drawn from SingIt limits in USDC on Base or Solana, and a required "search" scope on the key. That is exactly the cost/auth context annotations cannot express; only the non-idempotent flag (results vary between calls) goes unremarked.

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?

Two tight sentences: capability and return shape first, then usage routing, then cost and auth. No filler, and the most decision-relevant facts (what it returns, when to use, what it costs) are front-loaded.

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 correctly summarizes the return payload, and it covers cost, auth scope and the read_page follow-up. The only material gap is search-mode selection, which neither description nor schema addresses.

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 only 67% and the one enum parameter, `type` (auto/fast/neural/keyword), has no description in the schema and is never mentioned in the description — an agent has no basis for choosing a mode. `numResults` is only glossed as "defaults to a few" in the schema, with nothing added, so the description does not compensate for the coverage gap.

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 (searches the web via Exa) plus the return shape (titles, URLs, snippets), and names the sibling read_page as the follow-up for full pages. An agent can distinguish this from read_page or get_crypto_news 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?

"Use for current or niche information, then read_page for a full page" gives an explicit when-to and routes to the alternative. It stops short of stating exclusions (e.g. not for structured/known facts or non-public data), so it is clear context rather than a full when/when-not rule set.

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