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

Goes well past the annotations by disclosing price (USD 2, no free tier), per-IP daily caps, latency (1-5 s), row caps (5,000 rows/source), capped/complete flags, and a prompt-injection safety note about treating endpoint names/URLs as untrusted data. The mid-sentence aside about how delta_cursor behaves for agent_index_delta is confusing and partly belongs to the sibling tool, which costs it the top score.

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 name and price, and most sentences carry real information, but the whole thing is a semicolon-chained blob with no paragraphing. The delta_cursor/null-return digression about agent_index_delta dilutes focus on this tool, and query_agent_index appears late after other alternatives were already enumerated.

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?

Because an output schema exists, return values need no explanation, yet the description still covers price, auth, caps, latency, and a security caveat — enough to call correctly. The phrase "authorize client per-call and remaining daily caps to cover the price" is awkward and leaves the exact payment/auth flow slightly ambiguous.

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 single optional parameter is already documented as "Filter: exact source id." The description only echoes this with "optional source filter," adding no format, matching, or omission semantics beyond the schema, so the baseline 3 applies.

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 ("Download the current snapshot (gzipped)") with scope qualifiers (full snapshot, optional source filter). It explicitly distinguishes itself from three siblings — export_agent_index for filtered slices, agent_index_delta for refreshes, query_agent_index for narrower queries — so an agent can route without opening any 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?

Gives explicit when/when-not routing: "For a filtered slice use export_agent_index; to refresh an existing copy use agent_index_delta" and "for a narrower query use query_agent_index." Prerequisites (paid, no free tier, per-call authorization, daily cap) are stated up front.

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