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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description still adds material behavior: gzip encoding, the 5,000-row-per-source cap and capped/complete flags, ~1-5 s latency, USD 2 price with no free tier, and a per-IP daily cap. The untrusted-data warning about endpoint names and on-chain strings is exactly the kind of injection-safety context structured fields cannot convey.

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 the purpose, then alternatives, input, return shape, latency, price, and safety note in a tight progression. It is dense and the delta_cursor explanation is somewhat convoluted, but nearly every sentence carries decision-relevant information.

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 paid, capped bulk-download tool, everything an agent needs is present: cost, rate limit, latency, size cap, return-shape semantics, sibling routing, and a dependency/fallback rule. Returns are also covered by an output schema, so the description's brief summary of them is complementary rather than duplicative.

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?

The single parameter has 100% schema coverage, so the baseline is 3; the description goes beyond the schema by explaining what filtering does downstream (a filtered bulk of a capped source yields a null delta_cursor, requiring an unfiltered run). It stops short of detailing the maxLength or exact-match semantics, which remain in 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?

States a specific verb and resource ('download the current snapshot of the index') plus concrete scope: all sources, at most 5,000 rows per source, gzipped. It explicitly distinguishes itself from export_agent_index and agent_index_delta, so an agent can pick it without opening the sibling schemas.

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?

Names both alternatives and the condition that selects each ('filtered slice' → export_agent_index, 'refresh an existing copy' → agent_index_delta). It also gives a concrete fallback procedure for the delta_cursor=null case: run an unfiltered bulk and use its delta_cursor.

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