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

Annotations already declare readOnly=false, destructive=false, and openWorld=false, so the safety profile is covered. The description adds genuinely useful behavior: items are validated by the same checker as myinvois_invoice_generate and re-serialized canonically, so a bad item fails at save time and stored data is normalized. It is silent on the one thing idempotentHint=false makes critical: what happens when a template with the same name is created again (duplicate, overwrite, or error), and what the call returns.

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 sentences, front-loaded with purpose, then validation behavior, then the next step. The parenthetical enumeration of validated fields makes it dense, but every clause carries information an agent would otherwise have to discover by trial.

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 five-parameter write tool with no output schema, the description covers validation and one follow-on path but never says what myinvois_template_create returns (an id? the canonicalized object?), nor how the four metadata fields shape the saved template. Combined with zero required parameters, the agent knows how to build line_items_json but not what a correct full call looks like.

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 0%, so the description carries the full burden. It does an excellent job on line_items_json, spelling out the accepted fields, integer CENTS, basis points, and LHDN code-table validation. The other four parameters (name, notes, description, payment_terms) get no mention at all, and with zero required parameters it never says whether name is effectively mandatory.

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 verb and resource: 'Save a reusable line-item preset' so repeat invoice items 'do not get re-typed'. That distinguishes it from the invoice and generate siblings. It does not separate itself from myinvois_template_update, so an agent still has to guess at the create-vs-update boundary for a template with the same name.

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 states the triggering scenario clearly (a repeating invoice whose items you don't want to retype) and names the follow-on tool, myinvois_template_list, for pulling the items back out for a generate call. It gives no exclusion or alternative routing, such as when to call template_update instead of creating a second template.

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