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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior: it takes no arguments, it is the discovery step before tenant-scoped calls, and it discloses the access levels (read vs read+write) that come back per company. Slight gap in not saying what happens when the caller has exactly one company.

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-loads the identity purpose, then triggers, then the return shape; every clause carries information. The trailing 'Returns:' enumeration is dense and long, but it is justified because no output schema exists.

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?

With no output schema and no parameters, the description must carry the return contract, and it does — naming acting_as, connection, all_companies, default_company and the per-company fields. For a zero-arg discovery tool in a multi-tenant API, this is complete enough to call correctly on the first try.

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?

Zero parameters, so the schema baseline is 4, and the description correctly reinforces this with 'No arguments.' The `company` identifier formats (id, @handle, exact name) are explained, though they belong to sibling tools rather than this one.

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 specific resource and scope: the identity the connection acts as plus every company it can act for, with the 'a.k.a. whoami' gloss removing ambiguity. Nothing in the sibling list (list_carriers, list_shipments, get_usage) overlaps, so an agent can route here 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?

Gives explicit triggers — 'call it first when the user belongs to several companies' or 'when a call says access is denied' — and the follow-up action: pass `company` (id, @handle or exact name) to the other tools. It names both when to use it and what to do with the result, which is more than most list tools offer.

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