bitHuman

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral facts: the call is free, takes no arguments, needs only one invocation per conversation, and that only house characters can speak (real people/photos/custom voices excluded). It does not discuss failure modes or limits on the listing itself, but adds solid context beyond the 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?

Three tight sentences, front-loaded with what the tool lists and how the returned id is consumed. Every sentence carries distinct information (contents, usage cost/frequency, scope exclusion) with no redundancy.

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 zero-argument list tool with full annotation coverage and an output schema, the description supplies everything an agent needs: what it returns, that the id feeds the sibling tools, that a single call suffices, and which characters are supported. No material gaps remain.

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?

There are zero parameters, so per the rubric the baseline is 4. The description reinforces this with 'No arguments' and instead documents the shape of the returned records (id, name, short description, picture URL, talk), which is useful but not parameter semantics.

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 bitHuman house characters that can speak') and immediately clarifies what each entry contains (id, name, description, picture URL, talk flag). It also ties the resource to its siblings by naming the `character` argument used in make_character_video and talk_to_character, so an agent can distinguish it from them without opening a schema.

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?

Explicitly states the calling context: no arguments, free, read-only, and 'one call per conversation is enough,' which tells the agent not to loop on it. It also states the exclusion ('real people, photos and custom voices are not supported'), clarifying scope. It stops short of an explicit when-not/alternative routing statement beyond naming the sibling tools as consumers of the returned id.

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 only declare a non-read-only, non-destructive, non-idempotent local mutation; the description goes well beyond that with return fields (video_url expiring after 7 days, duration_seconds, share_url), an AI-labelling disclosure, concurrency and daily quotas, the same-input replay behavior, and a full error taxonomy with recovery actions. The only nuance is that the identical-input replay described is somewhat idempotent-like while idempotentHint=false, but the dominant new-video-with-quota behavior is non-idempotent, so this is not a contradiction.

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?

Everything stated earns its place given the number of failure modes and limits, and the purpose plus return values are front-loaded. It is a single dense paragraph mixing returns, limits, example, and errors, so light structural separation would help, but there is no filler.

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 two-parameter generation tool the description covers the purpose, the quota and concurrency constraints, the caching behavior, and every recoverable error with a next action, and an output schema exists so return-value detail need not be restated. Nothing needed to call it correctly 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% and the enum/min/maxLength are already in the schema, so the baseline is 3. The description adds real meaning beyond it: the ~19-second speech ceiling (~15 s typical), the word-for-word fidelity requirement, the excluded personal-information content, and a concrete example call.

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 ('Make a short video of one bitHuman house character saying `text` word for word, in its own voice') and distinguishes itself from siblings by routing conversational use to a per-reply pattern rather than talk_to_character and pointing at list_characters for character ids. An agent can tell what this produces without opening the schema.

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?

It gives explicit when-to-use guidance ('To hold a conversation in character, write each reply yourself and call this tool once per reply') and names the alternative for the failure case (unknown character -> call list_characters). Limits, retry timing, and the replay-on-identical-input condition are all stated, so usage conditions are unambiguous.

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?

Goes well beyond the annotations: discloses the 60-second self-terminating duration, the microphone requirement in the user's browser, the session_url return and what to do with it when no player is shown, and structured error semantics (unknown character -> list_characters with `talk` true; resting -> make_character_video still works). Annotations only cover the safety profile; the description carries the real behavioral burden.

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?

Front-loaded with the core action and duration before edge cases, and every clause carries information (duration, return value, error routing). It is dense rather than padded, though the error-handling tail makes it slightly longer than strictly needed for a one-parameter tool.

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 single-param tool with a full enum, an output schema, and annotations, the description supplies everything an agent needs: lifecycle, duration, return value usage, environment prerequisite, and both failure modes. Nothing material 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% and the enum enumerates every valid id, so the schema does the heavy lifting. The description still adds value by showing an example call and explaining how to validate an id (use one whose `talk` is true), which is meaning beyond the schema's plain 'a character id from list_characters'.

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 ('Open a live voice conversation with one bitHuman house character') and immediately distinguishes itself from siblings by naming list_characters for id lookup and make_character_video as the fallback. An agent can tell exactly what this tool does and does not do.

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 explicit when-to-use context (user presses Start, speaks via microphone), a hard limit (60 seconds, then ends by itself; call again for another), and a when-not path: if the service is 'resting', use make_character_video instead. The alternative is named with the condition that selects it.

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