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

Annotations already mark this destructive/non-idempotent, and the description adds real context the annotations cannot convey: the number is consumed immediately, there is no draft state, no e-mail is sent, and the response shape (series, number, PDF link) is described. The retry caveat is exactly the operational detail an agent needs for a non-idempotent write.

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-loads the critical distinction (proforma vs fiscal invoice) first, then behaviour, then prerequisites, then return, then failure handling. Six short clauses, each carrying unique information; nothing is padding.

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, nested-object write tool with no output schema, the description covers purpose, prerequisites, side effects, return content and error recovery. The only unaddressed element is the optional idempotency_key, which the 94%-covered schema documents on its own.

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 description coverage is 94%, so the schema carries the parameter burden and the baseline is 3. The description adds no per-parameter meaning beyond steering the agent to the VAT-rate and series lookup tools, which is useful routing but not parameter documentation.

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?

Specific verb+resource ("Create a PROFORMA") with an immediate disambiguation from the sibling it is not ("not a fiscal invoice"). The "preferred first step" framing tells an agent where this sits relative to oblio_issue_invoice without opening either 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?

Explicit prerequisites are named with the exact sibling tools to call first (oblio_list_vat_rates, oblio_list_series, plus client/lines checks), and retry behaviour is stated: "Not retried: if the reply is an error, look in Oblio before repeating." This is when-to-use, what-to-prepare, and when-not-to-retry in one compact block.

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