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

Annotations declare a non-read-only, non-destructive creation. The description goes well beyond that: it discloses that nothing is issued or sent at creation time, that activation triggers automatic Veri*factu finalization and emailing to the customer, and what the return payload contains. This is exactly the lifecycle context the annotations cannot convey.

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-loaded with the core action and draft state, then the activation path, then the return value. Three sentences with no filler, though the bilingual parentheticals (factura recurrente / suscripción, borrador) add slight density without much decision value.

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 15-parameter creation tool with no output schema, the description supplies the lifecycle and activation context an agent most needs, plus the return shape (id, name, frequency, next invoice date). It stops short of explaining default behaviors for tax_rate, payment_days, and items, which an agent might otherwise assume.

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 only 47% across 15 parameters, but the schema itself describes the highest-risk ones (is_active, auto_send, auto_finalize, start_date, end_date, description, product_group). The description reinforces the draft/activation semantics of is_active and the automatic emailing implied by auto_send, but it adds little on the remaining bare parameters such as items, tax_rate, payment_days, and retention_rate.

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 and resource (create a recurring invoice profile) and immediately disambiguates it from siblings by describing it as a saved template that generates invoices on a schedule, distinct from generate_recurring and update_recurring which are named. An agent can select this tool without opening any 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?

Explicitly says the profile is created as a draft and that to start the series the agent should confirm date/frequency with the user and then call update_recurring with is_active=true. The when-to-use and the alternative (update_recurring) are both named along with the precondition for switching.

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