create_task

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

With no annotations present, the description carries the full behavioral burden and does so unusually well: it states the created status (pending), that claim_next_task/claim_specific_task skip tasks with non-terminal predecessors (listing done/deferred/skipped/out_of_scope), that predecessors must share the plan, that cycles are rejected at insert, that the board sync always fires so a draft GitHub Projects V2 item lands in Backlog, and that Slack is opt-in with a stated default and rationale. This is more disclosure than most annotated tools provide.

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 most important fact (what is created, in what status) is front-loaded, and the dependency explanation is grouped coherently before the sync/Slack behavior. It runs long and packs several clauses per sentence, but virtually every sentence carries distinct operational information rather than filler.

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 zero-annotation, no-output-schema mutation tool with 11 parameters, the description covers behavior richly but leaves the majority of the input surface undocumented — notably as_agent, ExternalKey, ReferencePointer, and Paths, which look like they have protocol significance. An agent can call this correctly only for the PlanId/DependsOn/NotifySlack path.

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 0% across 11 parameters, so the description must compensate, and it only does so for two: DependsOn (dependency/skip semantics, same-plan constraint, cycle rejection) and NotifySlack (default false and why). Paths, Title, PhaseId, Priority, as_agent, ExternalKey, ReferencePointer, Description, and PlanId are left entirely unexplained, so an agent must guess at their formats.

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, and initial state: 'Create a new task on a plan, in pending status.' That is enough to separate it from read/claim siblings like claim_next_task. It does not, however, distinguish itself from the sibling create_tasks (bulk variant), which an agent would plausibly confuse it with.

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 names the callers ('orchestrators that decompose larger work units', 'admin tools that import work from external sources'), which implies usage context, but gives no explicit when-to-use-vs-alternative instruction and never mentions create_tasks or set_project_slack as related tools. The rule 'pass true to post a task.created message' is the closest thing to actionable guidance.

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