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

Annotations only declare write/non-destructive/closed-world; the description adds substantial behavior beyond that — the call is never performed directly, returns status='confirmation_required' with an action_id and plan_token, and the write only lands after confirm_action. Attribution to the caller's employee record is also disclosed, which materially affects what the agent is creating.

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 action and scope, then a clearly labeled CONFIRMATION block. Slight redundancy between 'runs the propose→confirm write gate' and the CONFIRMATION paragraph, but every part carries useful information and there is no filler.

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 single-parameter, non-destructive mutation with no output schema, the description covers the critical unknown — the two-step confirmation flow and the fields returned — so an agent can call it correctly. It stops short of describing failure modes (e.g., duplicate organization names) or what the final confirmed result contains.

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% for the single 'title' parameter, and the description only says "Provide 'title'" — it does not explain what the title represents (organization name? display label?) or any uniqueness/format expectation beyond the max length in the schema. Adequate but does not compensate for the coverage gap.

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 states a specific verb and resource ('Create an organization (account) in the ERP') and adds scope the name does not carry — creation happens under the caller's company and is attributed to the caller's employee record. It is clearly separable from sibling creation tools like erp_create_contact or erp_create_project, though it never explicitly names an alternative.

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 the operative usage condition an agent needs: the call is additive and goes through a propose→confirm gate, so the real write requires a follow-up with the returned action_id/plan_token via confirm_action. There is no explicit 'when not to use' or guidance on duplicates/name conflicts, which keeps it below a 5.

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