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

Annotations already declare non-read-only, idempotent, non-destructive and closed-world, so the bar is lower; the description still adds real context by spelling out that reusing the Idempotency-Key returns the existing task rather than creating a duplicate, and that the call 'sends nothing' (no message or notification side effect). The idempotency explanation is partly a restatement of idempotentHint=true, but it adds the concrete return behavior. It does not describe what the created task object looks like in the response.

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 important content (purpose, due_at timezone rule, idempotency, no side effects) is front-loaded and easy to scan. However, the closing two sentences are near-duplicates: 'Reusing an Idempotency-Key returns the existing task' and 'Retrying with the same idempotencyKey and input returns the first result instead of repeating the action' say essentially the same thing, so one of them does not earn its place.

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 three-parameter mutation tool with nested body/params objects, no output schema and only 33% schema coverage, the description covers the essentials an agent needs: what it creates, where, the timezone contract for due_at, and the idempotency contract. The main remaining gap is the shape of the returned task, which the agent cannot learn from anywhere since there is no output schema.

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 only 33% (only idempotencyKey is documented inline), so the description has to compensate and largely does: it explains that due_at is an ISO 8601 timestamp with an offset interpreted in the user's local time zone ('Thursday 10am' means 10:00 local), and it identifies engagementId as the pipeline contact identifier. The title parameter is only conveyed by example. This is a meaningful lift over the bare schema.

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 states a specific verb and resource: it 'adds a follow-up task' with a concrete example ('Call Dana') 'to one pipeline contact by its engagement ID'. That is unambiguous and scoped to a single contact. It does not explicitly distinguish itself from updateContactTask or listContactTasks, so sibling differentiation is left to the reader.

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 gives a clear triggering context ('Useful when the user wants a reminder to follow up with a contact'), which is exactly the situation that selects this tool. It also implies the prerequisite of an existing pipeline contact via the engagement ID. It names no exclusions or alternatives (e.g. updateContactTask for editing an existing task), which keeps it short of a 5.

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