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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond them: output is a read of current state, personal data (NIN, DOB, phone, addresses) is deliberately excluded, invalid fields return names only, and CAC's reason/fix_path items appear only for a queried registration. It stops short of covering permissions, freshness/caching of the status, or error behavior for an unregistered business_id.

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?

Purpose is front-loaded in the opening clause, and the long field enumeration is justified because there is no output schema to carry the return shape. The single sentence is dense and comma-chained, but almost every clause adds distinct information; only the trailing 'those are on the registration page' is arguably optional.

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?

With no output schema, the description properly carries the return-value burden and does so comprehensively, including what is deliberately omitted. Gaps remain around failure modes (unknown or foreign business_id), whether status is live versus cached, and any authentication expectations, but for a single-parameter read tool it is close to sufficient.

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?

Only one parameter exists and schema description coverage is 100%, with the schema itself telling the agent to source the id from list_my_businesses. The description adds only indirect meaning by framing the id as identifying one of the user's registrations. With the schema doing the heavy lifting, the baseline 3 is appropriate.

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 ('Read where one of the user's registrations stands') and then enumerates exactly what that state comprises: status, stage, next action, action_path, per-section done/missing/invalid fields, document statuses, payment status, NIN confirmation, and CAC reason with fix_path. This is far more than a restatement of the name and gives an agent a concrete picture of the payload, distinguishing it from narrower siblings like get_cac_documents or get_action_status.

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 phrase 'one of the user's registrations' implies usage for a known business_id, but the description never states when to choose this tool over refresh_cac_status, get_action_status, or get_cac_documents, nor any prerequisite like first calling list_my_businesses. The only routing statement is a field-level exclusion ('those are on the registration page'), which steers away from personal details rather than toward an alternative tool.

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