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

Beyond annotation hints, the description reveals that deletes are soft, that update is partial rather than replacement, and that restore consumes a deletedAt/ids from the list tool. These are meaningful behavioral details an agent needs before invoking a destructiveHint=true tool, and they do not contradict the annotations.

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?

The description is short and front-loaded, with the action list immediately following the purpose and each action carrying only its critical constraint. There is no filler or repetition.

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 12-parameter mutation tool with no output schema, the description plus rich schema descriptions and annotations cover the essential action semantics well. It could say more about response behavior or permissions, but the core invocation requirements are present.

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 high at 83%, and the schema already maps each parameter to actions, so a baseline of 3 is appropriate. The description adds semantic value by clarifying create-specific requirements, partial-update semantics, and the source of restore ids.

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 names the resource and enumerates the four actions (create, update, delete, restore), so the operation is unambiguous. It distinguishes itself from the read-only sibling only in the restore sentence, referencing companies_list, so sibling differentiation is partial rather than fully explicit.

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 per-action conditions: create requires name, update leaves omitted fields unchanged, delete is soft and should be confirmed first, and restore uses deleted ids from companies_list. This is strong action-level guidance, though it does not broadly direct agents to companies_list for lookup before update or delete.

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