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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower, yet the description adds real substance: what each result contains (voice ID, lane, what the voice does, what was studied, strengths and limits, status) and the ordering rule 'featured voices first' when the query is omitted. That ordering behavior is nowhere in the structured fields. It does not mention pagination or rate limits, keeping it below a 5.

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, front-loaded with the activation trigger before the mechanics, and every sentence carries weight. There is minor redundancy between the lane/effect enumeration and the identical wording already present in the query and lane schema descriptions, which keeps it off a 5.

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?

The tool has an output schema and full schema-description coverage, so the description needn't explain return values in detail; it nonetheless summarizes result contents. Combined with the trigger condition, semantic query guidance, and empty-query behavior, an agent has everything needed to invoke it correctly on the first try.

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%, so a 3 is the floor, but the description genuinely enriches the 'query' parameter by explaining it accepts a name, a lane, or a semantic description of the desired effect, illustrated with 'a roast, a launch post, a plain explanation, a speech'. It also restates the omit-to-list-all behavior that makes all three parameters optional, which clarifies the zero-required-parameter design.

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 gives a specific verb and resource ('Search Silvertongue's famous writing voices') and enumerates the three search dimensions: name, lane (with the full lane list), and intended effect. Read together with 'Call this first', it clearly positions the tool as the discovery entry point ahead of the get_voice/get_voice_packet retrieval siblings.

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 opening sentence supplies an unusually concrete trigger: use it whenever the user asks for writing 'as, like or in the voice of' a named person or character, 'even if they don't mention Silvertongue'. That covers the hard case where the agent wouldn't otherwise know to reach for this tool. It stops short of naming the alternative retrieval tools or stating when not to call it, so it is strong context without explicit exclusions.

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