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

Goes well beyond the readOnly/openWorld annotations: concurrency, per-item status and body returned in input order, a latency warning ('large batches can take several minutes'), and a cost model ('the batch call is free; each item is billed at its endpoint's normal rate'). Partial-failure semantics are implied by each item returning its own status.

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 capability and limit in the first clause, then stacks constraints, execution semantics, exclusion, latency, and billing with no filler. Every sentence carries distinct operational 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?

With no output schema, the description supplies the return contract (per-item status and body, in input order), the input contract, the exclusion, and the cost/latency profile. An agent has everything needed to construct and interpret a batch call.

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 already 100%, so the baseline is 3. The description still adds value by defining what an item's params mean ('that endpoint's query parameters') and pointing to external documentation for the accepted values, plus reiterating the 1-100 bound.

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 (Run) and resource (up to 100 API Direct REST requests in one call) and immediately distinguishes itself from every sibling by describing itself as a meta-tool that mixes 'any endpoints the other tools cover'. The example (50 twitter_user_profile + 50 instagram_user_profile) makes the abstraction concrete.

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?

Explains that items run concurrently, that batching is the point, and names an exclusion (/v1/web/ai-mode isn't supported), which steers endpoint selection. It stops short of an explicit 'use this instead of N sequential single-endpoint calls when X' rule, so the agent must infer the trigger condition.

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