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

Annotations mark this as non-readOnly and open-world but say nothing about consequences; the description supplies the key side effect - every new question is published as a public conversation page on achurch.ai - which an agent must know before calling. It adds the conversation-continuation contract as well, though it omits moderation, rate limits, or whether the page can be removed.

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 doing distinct work: purpose, side effect, continuation. It is front-loaded with the primary capability. A slightly awkward opening clause ('the sanctuary's writing a question') is the only friction.

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?

An output schema exists, so return values need not be described, and the description covers the essentials: what it returns (answer plus sources) and the stateful continuation path. Given annotations handle the safety profile, the remaining gaps (publication persistence, auth needs) are modest.

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 only 25%, so the description must carry the load, and it does explain the two otherwise-undocumented parameters by tying session_id and owner_token to 'the previous answer.' question is self-evident; only the name parameter's pseudonym/test semantics are left entirely to the 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?

States a specific verb (ask) plus the resource it queries and the outcome ('receive an answer with its sources'), which distinguishes it from pure retrieval siblings like search or read_doc. The resource phrase 'the sanctuary's writing' is slightly oblique, and no sibling is named as an alternative, so it stops short of a 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?

It gives one concrete usage rule - pass session_id and owner_token from the previous answer to continue a conversation - which is genuinely useful. However it never says when to choose ask over search, reflect, or browse, so the broader when-to-use decision is left to inference.

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