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

Annotations already declare destructive=true, idempotent=false, openWorld=false, so the safety profile is covered; the description adds genuinely new behavior — cross-tool routing/refusal semantics, org auto-resolution and the refusal-with-list failure mode, and that the return value is the raw upstream JSON. Minor gap: it references `risk` without explaining its values, and does not describe behavior on invalid `arguments` or upstream errors beyond the org case.

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 operation class, then the routing rule, then the parameter caveat, then the return value — no filler or restated name/title. Every clause, including the source hint for `risk`/`call_with`, carries actionable 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?

For a generic destructive dispatcher with no output schema and zero schema description coverage, the description supplies the routing model, scoping rules, and return shape, which is what an agent needs to invoke it correctly. Residual gaps are error handling for malformed `arguments` and any warning that deletions are irreversible beyond the destructiveHint annotation.

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 description coverage is 0%, so the description must carry the load, and it does for two of three parameters: `organization_id` gets scope meaning, optionality, and both fallback branches; `arguments` gets the constraint that it must conform to the operation's inputSchema. `name` is only implied as the operation identifier via 'Invoke an Anyreach operation' — workable, but never stated as the exact field semantics.

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 concrete verb and resource class: invoke an operation that edits or deletes existing entities, with an explicit enumeration (agents, knowledge bases, widgets, labels, credentials, custom tables, campaign settings). The edit/delete framing plus the note that other call tools 'refuse it' separates it from call_create_tool, call_read_tool, and call_live_tool without the agent needing to open any 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?

Explains the selection mechanism directly: the operation's `risk` and `call_with` (obtained from search_tools or describe_tool) designate which call tool executes it, and the others refuse. It also gives a concrete decision procedure for the optional `organization_id` — omit when there is one org, ask the user which one when several, then retry.

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