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

With no annotations provided, the description carries the full burden and does well: it discloses the verification step, the failure mode (returns CONSIGNMENT_NOT_FOUND for unknown IDs), the response markers ('status: DRAFT_GENERATED', 'actions_executed: []'), and that output copy is Bengali WhatsApp text plus a carrier escalation ticket draft. It stops short of stating permission requirements, rate limits, or whether repeated calls regenerate or reuse drafts.

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?

The key constraint — draft-only, no actions executed — is front-loaded in the first sentence and reinforced with concrete output keys. There is mild redundancy, since 'draft-only', 'GENERATION-ONLY TOOL', and 'for manual merchant execution' restate the same idea three times, but no sentence is genuinely wasteful.

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 seven-parameter tool with no output schema and no annotations, the description covers the important unknowns: the verification prerequisite, the error case, the return payload shape, and the no-side-effect guarantee. Remaining gaps are secondary — courier/consignment mismatch behavior and whether issue_type-specific fields are required in practice.

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 100%, so the schema already documents all seven parameters including the two enums, and the baseline is 3. The description adds only the meaning of consignment_id (it is verified, not merely consumed) and does not explain how issue_type drives which draft fields matter, such as reschedule_date or corrected_address.

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 pairs a specific verb with a specific resource — verify a consignment exists via 'track_parcel' and generate draft-only NDR re-engagement copy — and explicitly labels itself a GENERATION-ONLY TOOL that produces 'whatsapp_draft' and 'courier_ticket_draft' rather than executing anything. This is distinguishable from the sibling 'track_parcel', which it names as an internal dependency.

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 makes clear the tool is for draft generation that requires 'manual merchant execution', which tells an agent the output is not an action taken, and it signals that consignment verification is handled inside this call rather than by a separate 'track_parcel' invocation. It does not state explicit exclusions, such as when to prefer escalating via another path or what to do for couriers not in the enum.

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