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

Annotations are sparse (all boolean hints false), so the description carries the transparency burden. It adds genuinely behavioral guidance beyond the annotations: the IMPORTANT rule for selecting response_type by outcome ('text' for info collection, 'photo' for visual verification, 'checkbox' only for simple confirmations) and the routing warning about the agent's inbox. It stops short of describing side effects or confirmation behavior of a state-changing write, but the delivered guidance prevents the most likely agent errors. No contradiction with 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, each with a distinct job: purpose, critical decision guidance, and inter-tool routing. The most important operational warning (response_type) is front-loaded immediately after the purpose, and the alternative-tool note is deliberately separated with 'NOTE'. Every sentence earns its place; there is no filler, boilerplate, or meta-commentary.

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 mutating tool with no output schema and a moderately complex input (array of task objects with ten properies), the description covers the highest-risk decisions: correct response_type selection and correct tool routing. Combined with the 100%-covered schema, an agent can invoke it correctly. The remaining gaps — what is returned on success, confirmation/created IDs, prerequisites like the event existing — are not fatal given the informatinal depth of the schema, but they keep it from being fully complete.

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% and the schema itself is unusually rich — the response_type parameter already contains a 'CRITICAL:' note covering text/photo/checkbox/choice semantics, and assigned_to explains UUID validation and worker-portal matching. The description's response_type summary therefore largely distills information alread in the schema rather than adding new meaning. It does provide a one-line memorable heuristic and reinforces the bulk-creation capabilit, which is marginal value over the baseline of 3.

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 opens with a specific verb-resource-target triplet: 'Add one or more tasks to an event (task list)' and adds a meaningful capability ('Supports bulk creation'). It explicitly distinguishes itself from the closest confusable sibling, tascan_dispatch_to_agent, stating that tool 'routes directly to the agent's inbox' — so an agent can pick the right tool without opening 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?

The NOTE sentence gives an explicit when-not-to-use condition ('To dispatch tasks to the Claude Code agent running on Mike's PC, use tascan_dispatch_to_agent instead') with a named alternative and its benefit ('zero configuration needed'). The main use case (adding tasks to an event) is implicit in the first sentence. It does not contrast with tascan_add_subtasks, but that gap is minor since the resource names already differ.

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