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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, and the description adds real value on top by disclosing the state-dependent consequence that no bookings or reports exist while has_accounting is false. It also documents the return fields even though no output schema exists. It stops short of mentioning error conditions or what happens with an invalid company_id, so it is not quite exhaustive.

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?

Three tight sentences: what it returns first, when to call it second, and the state-dependent navigation consequence last. No filler and the highest-value information is front-loaded.

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, the description compensates by naming the returned fields and their meaning, and it explains the downstream implication of has_accounting being false. For a single-parameter read tool, an agent has everything it needs to select and call this correctly.

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 100% and the single parameter already carries a description tying it to list_my_companies' company_id values. The prose adds no format, constraint, or provenance detail about company_id beyond what the schema states, so the baseline 3 applies.

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 opens with a specific resource ('The company's setup state') and enumerates the exact fields returned: has_accounting, accounting status, VAT registration, chart of accounts, and trial dates. This is clearly distinguishable from the reporting and bookkeeping siblings, which none of them return setup/trial data.

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 three explicit triggers (user asks about setting up/starting accounting, wonders why the start-accounting invitation appears, or asks about the trial) and names the alternative path, ui_navigate to new_accounting, when has_accounting is false. That is precisely the when-to-use / what-to-do-instead guidance an agent needs.

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