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

Annotations supply only destructiveHint=true, so the description carries most of the burden and does so well: it discloses the non-idempotent create semantics, the required-field minimum, the outward-effect scope ('nothing is sent to the client'), and the underlying endpoint POST /clients/create. These are traits an agent cannot infer from the annotations.

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 tight sentences; the WRITE marker and core action are front-loaded, and every clause carries a distinct, non-redundant fact (dupe risk, required field, no outbound send, endpoint).

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 13-param create tool with no output schema and minimal annotations, this covers the mutation-risk and safety questions an agent needs answered. The remaining gap is the response shape (e.g. whether a client id is returned for follow-up calls), which the absence of an output schema makes slightly more relevant.

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 62% across 13 params, and the description only restates that 'name' is required, which is already in the schema's required list. It adds no format, constraint, or cross-reference detail for the other fields (e.g. country_id's list_countries link exists only in the schema). Baseline 3 for a partially documented schema with no compensating prose.

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?

Opens with 'WRITE: adds a new client to the SuperFaktura address book', giving an explicit verb (adds), resource (client), and destination (address book). The note that only the name is required and the POST endpoint pin it down unambiguously against siblings like superfaktura_get_client and superfaktura_add_contact_person.

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 names the exact alternative to consult ('check superfaktura_list_clients first') and explains the condition that motivates it (non-idempotency: two calls create two clients). It also sets expectations about side effects with 'Nothing is sent to the client'.

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