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

Annotations already declare this as a non-destructive write (readOnlyHint=false, destructiveHint=false), so the bar is lower, and the description does add real behavior: addresses are normalized, duplicates are updated rather than rejected (upsert semantics), opted-out people are skipped, and search limits are honored. It still omits what the call returns, whether the import is synchronous or partial-success, and what happens when the 100-item cap is exceeded.

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?

A single front-loaded sentence with the cap and required field stated first, followed by a compact behavior clause. The long parenthetical field list is dense but every entry carries parameter information, so little is wasted.

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 nested-payload mutation tool with no output schema, the description covers ingest rules and safeguards well but leaves the identity of the target ('id'), the response shape, and error/partial-import behavior unexplained. An agent could construct the call but would not know what to expect back.

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?

With 0% schema description coverage the description must compensate, and it largely does: it enumerates every item field (name, handle, headline, jobTitle, company, location, followers, website, publicEmail, publicPhone, summary, score, scoreReasons), flags profileUrl as mandatory, and constrains score to 0-100. The one required top-level parameter, 'id', is never explained, which keeps this short of a 5.

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 (Importer) and resource (profils publics) with a hard cap of 100 and the source implied ('lus dans le navigateur'). An agent knows exactly what the tool ingests, though it does not name how it differs from siblings like import_contacts or import_collection_rows.

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?

There is no explicit when-to-use or when-not-to-use guidance and no alternative tool is named, even though import_contacts, bulk_contacts and exclude_prospect sit in the same neighborhood. The only context is implicit in 'lus dans le navigateur', which suggests browser-captured profiles but never states the selection rule.

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