Rumble

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond that with cost behavior: per-resource credit prices, a variable transcript pricing model (captions vs AI transcription scaled by video length), the guarantee that failures are free, and that the result reports what was charged and remaining balance. It also discloses pagination semantics (cursor chains, and in the schema that changing `sort` restarts the chain) and the free cached-read tradeoff of max_age_days. This is exactly the billing/rate context annotations cannot express.

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 invocation model, then a scannable bulleted resource list where each line carries unique information (args, cost, paging). Some redundancy with the schema remains — 'pass it back unchanged' for cursor repeats the schema description verbatim — and the pricing caveat for transcripts is dense but justified. Overall tight for the amount of distinct information conveyed.

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 five-resource dispatcher with no output schema, the description covers the things an agent would otherwise guess wrong: cost per call, failure billing, pagination, and caching. It also partially describes the response ('says what was charged and what is left'). It stops short of describing what each resource actually returns field-wise, though that is arguably out of scope for a gateway.

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%, so the schema already defines every parameter, making 3 the baseline. The description adds meaning on top: it maps which resource consumes `handle` vs `url`, documents the optional `allow_long_transcription` flag with its pricing consequence, and explains the deliberate top-level-vs-`params` convention plus the fallback to `describe` for types. The added cost-to-parameter coupling (max_age_days buys a free cache hit) is real value beyond 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?

The lead line names the platform and data types, and the Resources block enumerates five concrete operations (channel.videos, search, video, video.comments, video.transcript) with their required arguments. The platform name plus resource list clearly distinguishes it from siblings like youtube, tiktok, or truthsocial. The opening sentence alone ('Data from Rumble: posts and videos, comments, transcripts') is vague, and the real specificity lives in the bullet list rather than a single verb+resource statement.

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 solid invocation mechanics: pick a resource, pass its parameters as top-level arguments, put extras in `params`, pass the cursor back unchanged, and use max_age_days for a free cached copy. What's missing is when-to-use guidance relative to alternatives — siblings `search`, `get_comments`, and `get_transcript` overlap with this tool's resources, and the description never says which to prefer. So usage is implied and operationally clear, but no exclusions or alternative routing are stated.

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