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

Annotations only cover the safe-read profile; the description adds the cost model ($0.03 via x402, USDC on Base), the fact that under-30-post results, refusals and errors are not charged on Base but may be on other rails, and the terms link. It also discloses what the response contains and deliberately omits (links only, no text or usernames, Bluesky DID included), which is real behavioral context an agent cannot infer.

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 and the 'NOT a poll' correction, then constraints, then output shape, then pricing. Dense but well ordered; the parameter restatement and terms URL are the only near-wasteful parts, and both are arguably load-bearing.

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?

No output schema exists, yet the description explains the return payload (per-side share with 95% interval and n, per-source counts, links-only, caveats). Combined with the refusal rules and billing terms, an agent has everything needed to call it and interpret results.

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 100% and every parameter detail in the description (sides 2-4 default yes,no; window 1-30d) is already documented in the schema, so it adds no new meaning. 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 and resource ('Hacker News and Bluesky opinion split') and preemptively disambiguates from a poll, which is the most likely misreading. No sibling does anything similar, so there is nothing else to differentiate against.

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 exclusion domains (elections, health, a named person's conduct) and a minimum-evidence threshold (under 30 decided posts refuses), so the agent knows when calls will fail. It stops short of naming alternatives, but the sibling list contains none that overlap.

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