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

Annotations only declare readOnlyHint=false, so the description carries real weight here: it discloses the confirm-gated preview-then-execute flow and the cross-field dependency (GSTIN requires legalName + address). It stops short of saying what happens to settings not supplied.

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 compact clauses, front-loaded with the action, then the key side effect, then the safety mechanism. No filler sentences.

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 mutation tool with no output schema and a nested input object, the description covers the important behaviors but leaves a consequential ambiguity: since all settings fields are optional, it does not say whether this is a partial merge or a full replace, and it says nothing about organization scoping.

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?

With only 33% schema description coverage, the description successfully compensates for the two most consequential inputs: gstin's legal effect and confirm's gating semantics. The remaining fields (footerNote, invoicePrefix, address, legalName) are left to the schema names alone.

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?

"Save invoice settings" names a specific verb and resource, and the GSTIN sentence clarifies the primary side effect. It does not explicitly distinguish itself from the sibling get_invoice_settings, but the write-vs-read split is self-evident.

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?

The description implies when to use it (when configuring GST invoicing) but never states alternatives or preconditions beyond the GSTIN dependency. It also omits that get_invoice_settings should be read first to see current values.

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