Batch add items

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

Annotations (readOnlyHint=false, destructiveHint=false) establish the write-not-destructive profile; the description adds behavioral context beyond that: dryRun preview, stopOnError, and atomic rollback. The rollback disclosure is genuinely meaningful — the agent learns failed batches delete already-created objects. Nothing contradicts the annotations.

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?

Three sentences with zero filler: purpose first, then a compact feature summary, then an actionable pre-condition warning. Every sentence earns its place and nothing restates the title or schema verbatim.

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?

This is a complex tool (nested item array, atomicity, rollback, dryRun, idempotency), but the schema exhaustively documents all parameters, an output schema exists, and annotations cover the safety profile. The description covers purpose, key behaviors, and the critical duplicate-prevention workflow. Only minor gap: no explicit contrast with single-item add siblings, though the batch scope is stated.

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%, and the schema's per-property descriptions already explain tempId/parentTempId wiring, date parsing semantics, atomic/stopOnError interaction, and idempotencyKey. The description names the key semantics (hierarchy wiring, dryRun, atomic rollback) but adds no depth that the schema lacks, 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 ('Add'), resource ('tasks or projects to OmniFocus'), and scope ('multiple... in a single operation'). The batch nature distinguishes it from single-add siblings (add_omnifocus_task, add_project), and the mention of 'add' separates it from batch_edit_items. The cross-reference to find_similar_tasks further orients the agent.

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?

The final sentence gives explicit pre-use guidance: 'Before adding tasks that may already exist, call find_similar_tasks for each name and drop or replace any item with a strong match' — naming the alternative tool and the condition that triggers it. It also explains the rationale ('batch creation multiplies duplicates'). It does not explicitly exclude single-item add tools, but the 'multiple... in a single operation' phrasing makes the batch context clear.

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