AI Anyone

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

Beyond the annotations, the description discloses that the tool advances a stateful debate, returns the next speaker and their private aim, and eventually signals completion with 'done'. This is useful behavioral context that the false readOnly/idempotent hints only partially convey.

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: purpose first, then loop termination, then flag semantics, followed by a precondition. Every sentence earns its place and the critical usage constraint is front-loaded.

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 adequately explains what the tool returns (next speaker, private aim, and a done signal) and how to sequence calls. It could say a bit more about what 'done' means or any failure modes, but the core loop is complete.

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 the baseline is 3. The description adds minor clarification for addressed_other and conceded, but these largely restate the schema descriptions. It does not add significant new parameter meaning beyond what the input schema already provides.

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 clearly states the action: submit the line you wrote and receive the next speaker and their private aim. It also distinguishes this from the sibling debate_two_people by framing it as the continuation of an ongoing debate turn.

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 says to keep calling until it returns done, which defines the loop usage. It also states the prerequisite: only reachable after debate_two_people, giving a clear when-to-use and when-not-to-use condition.

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?

The description discloses substantial behavioral detail beyond the annotations: it runs a live exchange, privately hands on one speaker and one aim at a time, hides the other side from each speaker, controls turn order, and ensures neither position is predesigned to lose. It also names the return artifacts (matchup card, transcript). No contradiction with 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?

Every sentence earns its place: trigger phrases, the contrast with scripted/one-sided output, the mechanics of the live exchange, and the return values. The most important usage guidance is front-loaded, and there is no filler or repetition.

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 tool with only two fully documented parameters and no output schema, the description covers the essential operational context: when to invoke it, how the debate flow works, the fairness mechanism, and what the agent will receive in return. An agent can invoke it correctly without additional information.

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 the schema already fully documents topic and mind_ids. The description adds helpful examples and context but does not need to explain parameter formats further, so the baseline of 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 action — staging a live debate between two people — and contrasts it directly with summarization and scripted exchanges. This makes it easy to distinguish from siblings like speak_as_person and find_someone_to_ask even without opening their schemas.

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 explicitly says 'Use this when someone wants two people to actually argue rather than be summarised' and provides clear example phrasings. It also implies when not to use it, such as when a scripted or one-sided response is wanted, though it does not name sibling tools explicitly.

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?

It discloses the output format (grid of real people with portrait and role), the interactive behavior (each is ready to be spoken as), and the follow-up action (user picks one, conversation continues in that voice). This goes well beyond the annotations, which only mark the operation as read-only and idempotent.

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 deliver the trigger condition, example usage, output shape, and interaction flow. The most important usage guidance is front-loaded, and every phrase earns its place with 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?

With no output schema, the description compensates by explaining the return value and the follow-up interaction. All parameters are already documented in the schema, and the annotations cover the safety profile, so an agent has everything needed to select and invoke the tool correctly.

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?

The schema covers all three parameters with clear descriptions, so the baseline is 3. The description's examples ('stoicism', 'Nietzsche') loosely illustrate the query parameter but add no meaningful structural or semantic detail beyond what the schema already provides.

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 clearly states the specific action (find someone to learn from) and the resource (real people), with concrete example queries. It distinguishes from siblings by emphasizing 'has not named one yet,' which separates it from tools that probably require a named person or debate setup.

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 description gives an explicit trigger condition and examples, and the phrase 'has not named one yet' implies a when-not condition. However, it does not explicitly name the alternative sibling tool (e.g., speak_as_person) for cases where a person is already named, 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 already mark this read-only and non-destructive, and the description adds substantial behavioral context: it returns a rendered card plus a sourced dossier, details what the dossier contains, and discloses that the assistant will 'Adopt the dossier and answer as them from that point on.' This persistence behavior is exactly the kind of trait an agent needs to know.

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 trigger condition is front-loaded, followed by illustrative examples, return-value details, and the post-call behavior. Every sentence earns its place, and the description is dense without being bloated.

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 only one parameter and no output schema, the description fully compensates: it explains the return payload, the dossier contents, and the resulting persona adoption. Nothing essential for selecting or invoking the tool 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?

The input schema covers the single parameter mind_id fully with an example and a pointer to find_someone_to_ask, so the schema does the heavy lifting. The description does not add additional semantic detail about the parameter, so the baseline of 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?

The description states a specific verb and resource: 'hear FROM one specific person' and 'answer as them.' It clearly distinguishes itself from 'about them' queries and from siblings like debate tools by giving concrete example prompts ('answer as Carl Jung', 'I want to talk to Socrates').

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 explicitly opens with 'Use this when someone wants to hear FROM one specific person rather than about them,' which is a clear trigger condition. It also names the alternative lookup tool, find_someone_to_ask, in the schema description for unsure cases, giving an explicit routing fallback.

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