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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-derivable context: the caller is the host, invocation happens per-keystroke during typing (which explains the idempotentHint=false), and scope is limited to finished works. It does not describe result shape or ranking, but an output schema exists so that is not required.

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 sentences, zero waste. The capability is front-loaded and the critical call prohibition is placed second where it is still prominent. Nothing repeats the schema or annotations.

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 one-parameter read that is documented with an output schema, the description supplies what matters: who invokes it, when, and over which corpus. The only gap is what the query actually matches against, which the agent would need if it ever did call this tool.

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% and the single `query` parameter is already documented as "search text; may be empty." The description adds no matching semantics (whether query hits titles, composers, or tags) or handling of the empty-string case, so it sits at the baseline for a fully documented 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 and resource ("Search the user's finished VerseIn images and videos") plus the consuming surface (the composer @-mention picker). An agent instantly knows this is a mention-autocomplete search over a specific library subset, not a general media search.

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?

Contains an explicit, unambiguous exclusion: "Called by the host while the user types; assistants must not call it." This is exactly the kind of hard routing rule an agent needs, and it overrides any temptation to invoke the tool because it appears in the tool list.

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