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

Annotations already cover the safety profile (readOnly, openWorld, non-destructive, not idempotent), yet the description adds real behavior the schema cannot: server-side execution, background runs for long jobs, a full per-platform/per-scale credit table, the billing.display notice, and that a `handle` re-read is free. What is missing is any note on latency expectations beyond 'long', or why the call is non-idempotent despite the free re-read path.

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?

Purpose and output shape are front-loaded in sentence one, with pricing detail after. The credit table is long and its semicolon/dash notation is dense, but every line carries decision-relevant cost data. Slightly over-stuffed for a description, though not padded.

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 9-parameter, 1-required tool with no output schema, the description covers what comes back, what it costs, how plan-vs-execute resolves, and how to handle failure and billing messages. The only real gap is the absence of any sibling routing cue, which context conditions make more important given a crowded toolset.

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 and baseline is 3. The description nevertheless adds genuinely new meaning by mapping scale × platform onto credit prices, which lets an agent choose `scale` and `platforms` on cost grounds rather than guessing. The 'medium/large not offered' dash cases are not explained.

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 first sentence names a specific resource (brand/product sentiment) and enumerates the concrete outputs: attitude shares, top mentions, top-engagement posts with source links. That is far more specific than a tautology. It never names a sibling, though, so an agent must infer the split from 'research', 'trending' and 'search' on its own.

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?

Useful procedural guidance exists — costly or long runs quote a price first, `confirm` controls plan-vs-run, and errors route to error.fix — which is genuine when-to-run mechanics. But there is no statement of when to prefer this over the many sibling research/search tools, nor any exclusion. Usage is implied by the resource rather than argued.

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