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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint, destructiveHint=false), but the description adds genuinely non-obvious behavior: content is read live from the house's page at call time, the words are the house's and the Scripture is re-read from stored King James text, nothing is generated, and it is honest when no page matches. That failure-mode and provenance disclosure is exactly the value the description should add on top of 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?

The core purpose is front-loaded, but the middle is a sprawling catalogue of a dozen-plus situations that could have been compressed, and the final sentence about praying by name is confusing rather than informative. Some enumeration helps a free-text retrieval tool, but the sentence structure is not disciplined.

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 format needn't be explained, and the description covers source, provenance, and the no-match case well. The remaining gap is sibling positioning: with `pray_for_someone` and `ask_living_bread` present, the description should say how this differs, which it does not.

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% for the single `situation` parameter, so the schema already documents its format and the 120-char bound. The description's example queries restate the same idea as the schema's own example ("my daughter's surgery"), adding no syntax or matching semantics beyond it. Baseline 3 is appropriate.

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 states a specific verb and resource: it reads a hand-written prayer keyed to a situation from the house's library, with a concrete source (living-bread.org/a-prayer-for). The enumeration of covered situations makes the retrieval scope unambiguous. It stops short of 5 because it never distinguishes itself from the similarly named sibling `pray_for_someone` or `ask_living_bread`, leaving the agent to infer the boundary.

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?

Usage is implied through sample user phrasings ("a prayer for my mother in hospital", "a morning prayer", "pray for my marriage"), which helps the agent recognize a matching intent. However, no when-not-to-use condition or named alternative is given, and the closing sentence about praying "with the person by name" actively muddies the line against `pray_for_someone`.

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