Plan a new ChurchTools group

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

The description does add real value beyond annotations: it discloses the dry-run semantics and the duplicate-name refusal behavior. But it directly contradicts readOnlyHint=false by asserting 'Writes nothing', leaving the agent unsure whether state can change. The partial value is outweighed by the metadata conflict.

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?

Two short sentences, with the most decision-relevant fact ('Writes nothing') front-loaded. The second sentence on duplicate-name handling also earns its place by preempting a likely failure mode.

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 no output schema, the description should at least sketch the shape of the returned plan, since the agent likely needs to hand it to ct_execute_plan; it also says nothing about the nested 'fields' object or auth needs. It covers the key behavioral facts but leaves the return payload and the follow-up workflow unexplained.

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 every parameter is documented in the schema, including the groupStatusId value mapping (1 active, 2 pending, etc.). The description adds no parameter-level meaning of its own, so the baseline 3 for high coverage 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 and resource — 'returns a plan to create a group' — and the leading 'Writes nothing' immediately disambiguates it from a real create like ct_create_person. It does not name any sibling or distinguish itself from the plan-execution counterpart, so it falls short of 5.

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 dry-run framing implies the usage (call this to preview, then presumably execute elsewhere), which is the 'implied usage' level. However, it never names ct_execute_plan or any alternative, and gives no when-not condition, despite that being the single most useful routing fact for this tool.

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