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

Annotations declare readOnlyHint=false, which would normally imply mutation; the description usefully clarifies that analysis returns duplicate/invalid rows 'before any contact is added' and 'does not subscribe or message anyone,' plus the generation-pinning and request-ID replay semantics. This adds real context beyond the annotations, though the tension between readOnlyHint=false and the no-write behavior is left implicit.

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 two actions, then the per-action parameters, then the invariants (requestId reuse, generation pinning, no side effects) and the guide link. Dense but every sentence carries information; the choppy telegraphic style is efficient rather than padded.

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 two-action nested-payload tool with no output schema, the description covers both actions, their required inputs, what analysis returns, idempotency, and a workflow guide. Only the relationship to the sibling confirm/import tools is missing.

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?

The schema only exposes a free-form payload object with a vague 50%-coverage description, so the description carries the load by naming the actual per-action parameters (listId, storagePath under contact-imports/yourUid, totalContacts, requestId, jobId). That is meaningful semantics the schema does not provide.

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 specific verbs (analyze, get) on a specific resource (owner-uploaded NDJSON contact import) and its scope, with the second action (get reviewed import status) also named. The phrase 'before any contact is added' separates it from confirm_contact_import and import_contacts_to_list without opening their schemas.

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 routes the two actions: analyze needs listId/storagePath/totalContacts/requestId; get needs jobId. It also gives a recovery rule ('Reuse the same request ID after a lost response') and points to the workflow guide resource. It does not, however, state when to prefer this over confirm_contact_import or import_contacts_to_list.

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