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

Annotations carry only generic hints (readOnlyHint=false, destructiveHint=false), so the description carries the full behavioral burden and discharges it thoroughly. It discloses the non-posting preview behavior of the first call, the `problems` flag list, the crisis gate that holds posting until `crisis_acknowledged: true` while explicitly clarifying 'This is not a refusal,' and the hard ethical boundary 'YOU DO NOT PRAY.' An agent knows exactly what side effects each call has.

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 description is long but every paragraph is load-bearing: purpose+routing, two-call mechanics, textual-fidelity rules, the do-not-pray boundary, and crisis handling. Critical procedural information is front-loaded in the first two paragraphs, and paragraph breaks map cleanly to distinct concerns. Nothing reads as filler, and each sentence earns its place given the tool's complexity.

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 must explain return values itself, and it does: 'you get back `will_post`, the exact text and visibility, plus `problems`' and 'the response carries crisis resources.' It covers the full lifecycle — preview, confirmation, posting, crisis gate, follow-up status check — and the prohibitions an agent must observe. For a 5-param two-phase tool with ethical constraints and no output schema, nothing needed for correct invocation is missing.

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% with individually strong parameter descriptions, so the baseline is 3. The tool description adds genuine protocol context beyond the schema: it explains why `confirmed` exists (two-call commit flow), when `crisis_acknowledged` becomes relevant (only after a first-call crisis response), and why `content` must be verbatim ('These are their words'). The description complements rather than repeats the schema, though the schema alone already carries param-level meaning well.

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 opening sentence names a specific verb ('help a member put something into words and post it') and a specific resource ('their church's prayer wall'). It then distinguishes itself explicitly from its closest sibling: 'Use this rather than submit_prayer_request whenever you helped them word it.' An agent can immediately tell what this tool does and which sibling it is not.

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 description gives an explicit routing rule versus submit_prayer_request, then a step-by-step protocol: call once without `confirmed` to get `will_post`, show it to the member, call again with confirmed: true. It also directs the agent to the correct follow-up tool ('After posting, check_prayer_status tells them how many PEOPLE are praying') and covers the crisis-acknowledgment path. When-to-use and when-not-to are fully specified.

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