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

Beyond the annotations (openWorldHint, non-idempotent, non-destructive), the description discloses the return artifact (8-character code), its short lifetime (~1 minute), an intermediate 'code is being prepared' state with a 10-second retry cadence, and the authorization level required. That is exactly the operational behavior an agent cannot get from structured fields.

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 first clause, followed only by operationally necessary instructions (relay steps, expiry, retry, next tool, permissions). Every sentence earns its place; nothing is repeated from the title or schema.

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 only two well-documented params, no output schema, and light annotations, the description supplies everything an agent needs: what it returns, how long it lasts, how to handle the pending state, what to call next, and who may call it.

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 100%: phone (with country code example) and project_id (uuid, sourced from dosai_list_projects) are fully documented in the schema. The description adds no parameter-level detail beyond that, so the baseline 3 applies.

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 (connect), resource (the business's WhatsApp number), and the distinguishing mechanism (no QR, returns an 8-character code). This clearly separates it from the QR-based sibling dosai_get_whatsapp_connect_link without needing to open either schema.

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?

Gives the operating context (owner on the phone with that WhatsApp), the exact relay instructions, the retry rule when the code expires or is still being prepared, and names the follow-up tool dosai_get_whatsapp_status. It also states the permission requirement (admin or owner), leaving nothing to inference.

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