VoiceHue

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds value by specifying that only 'public' voices accessible to the key are returned and by enumerating the returned fields, though it says nothing about result size, ordering, or pagination.

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 short sentences with zero filler; the capability and returned fields come first, and the follow-up action is placed at the end where it is most actionable.

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 usefully compensates by naming the four returned fields, and the sole parameter is covered by the schema. It is nearly complete for a simple read tool, missing only ordering/pagination expectations.

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 optional 'language' parameter is fully documented in the schema, including prefix-matching behavior and examples. The description adds nothing about the filter, so the baseline 3 applies.

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 ('List the public VoiceHue voices a key can use') and names the exact fields returned (id, name, language, gender). It also distinguishes itself from its only sibling by telling the agent the output feeds 'text_to_speech'.

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?

'Pass a voice id to text_to_speech' makes the workflow role of this tool explicit — it is the discovery step before synthesis. It does not state any when-not conditions or edge cases (e.g., what to do with an empty list), so it stops short of full routing guidance.

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

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), so the description's job is to add context. It does useful work by describing the return payload (audio file plus a one-line summary with voice, characters, duration) and the character ceiling, but it says nothing about the non-idempotent nature, latency, or whether repeated calls with the same input are billed/regenerated — a real gap for an openWorld, non-idempotent generation tool.

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?

Four short sentences, front-loaded with the action, then the return value, then the limit, then the prerequisite — the ordering matches how an agent needs the information. Every sentence carries non-redundant content; nothing to cut.

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?

Absent an output schema, the description takes responsibility for describing the return value and does so concretely. It also covers the required-voice prerequisite and size limit; only error behavior and the implications of the non-idempotent annotation are left unaddressed, which is a minor gap for a four-parameter 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 description coverage is 100%, so every parameter is already documented, and the description adds no semantics beyond it — the MP3 default and 1,200-character limit are both restated from the schema, and the speed parameter is not mentioned at all. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ("Convert text to spoken audio with a VoiceHue voice") and immediately distinguishes it from the only sibling, list_voices, both in purpose and in prerequisite ordering. An agent can tell exactly which of the two tools produces audio.

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?

Gives an explicit prerequisite: "Use list_voices first to get a valid voice id," which is the main failure mode for this tool, plus a hard constraint of 1,200 characters per call. It stops short of stating when not to use it (e.g. no batching / long text handling), so it is clear context rather than a full usage rubric.

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