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

Annotations already declare destructive/openWorld/non-idempotent, and the description adds context beyond them: operations reach real people and live traffic, and the `organization_id` omission rule (single org auto-used, multi-org refused with the list, then ask and retry) is a concrete failure mode not encoded anywhere else. It stops short of stating irreversibility or confirming how the upstream refusal of the wrong call tool is surfaced to the caller.

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 purpose, then routing rule, then per-parameter semantics — a logical order with no filler sentences. The operation-type enumeration is long and only partially needed once the routing rule is stated, costing a little density.

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 3-parameter, no-output-schema, destructive open-world tool this covers the essentials: what it touches, how to pick it over siblings, how the org scope resolves, and that arguments must match the operation schema. Leaving `name`'s exact expected value implicit is the main residual gap for an agent invoking it cold.

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 0%, so the description must carry the load and it largely does: `organization_id` gets full semantics (scoped-by-default, auto-resolution, refusal-with-list behavior), and `arguments` is explained as needing to conform to the operation's inputSchema with the upstream JSON returned. The only soft spot is `name`, whose role as the operation identifier is implied ('the operation') rather than stated outright.

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 description gives a concrete verb ('Invoke') plus a precisely bounded resource class ('an Anyreach operation that affects live traffic or the world outside the platform') and then enumerates representative members (publishing, dialling, campaign edits, phone numbers, secrets). It explicitly distinguishes itself from sibling call tools by stating that each operation's `risk`/`call_with` names the single tool that will run it and 'the others refuse it', so an agent can route without opening a schema.

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 states the selection criterion (operations touching live traffic or the outside world) and points to search_tools/describe_tool as the source of the `call_with` field that decides among the call_* siblings, which is strong routing guidance. What's missing is an explicit when-not: it never says 'if the operation is read-only or a draft, use call_read_tool / call_change_tool instead', leaving the agent to infer the exclusions from the risk field.

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