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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the mutation profile is known. The description adds genuinely useful non-annotation context: writes persist to a shared profile read by every other server, hence the 'call it once, first' ordering. However, it never says whether omitted fields are preserved or cleared on a subsequent call, which matters a lot for a 16-parameter setter flagged non-idempotent — that ambiguity keeps it at 3.

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?

Two sentences, zero waste, and the most important facts — what it owns, where it lands, when to call — are front-loaded. No restating of the title or 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 16-parameter mutation tool with no output schema, the description covers the cross-server blast radius and call ordering an agent needs before invoking it. The remaining gap is update semantics (overwrite vs merge on repeat calls) and whether a return value confirms saved fields.

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%, so the baseline is 3; the description goes slightly beyond by grouping parameters into functional clusters (identity, address, VAT, bank, defaults including currency/tax rate/terms/prefix/timezone) that help an agent decide which are core versus optional defaults. It doesn't explain the three tax-rate aliases (vat, tax_rate, vat_rate) or the email/phone 'only if the user gave it' rule, but the schema already carries those.

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 verb+resource ('The ONE business profile... Save to the shared profile') and enumerates the exact fields it owns (name, address, VAT id, bank, defaults). The phrase 'the ONE business profile for the whole suite' cleanly separates it from siblings like client_add and invoice_create, which operate on other entities.

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?

'Call it once, first' gives explicit sequencing and frequency guidance that an agent can act on before calling any invoice or client tool. It stops short of naming alternatives or stating what to do if the profile already exists (re-call vs read), which would have made it a 5.

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