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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It names potentially destructive operations such as 'delete chats' and 'clear history' but never explains side effects, reversibility, confirmation requirements, or permission expectations. The version string 'Clients API v2.28.12' adds context but no behavioral clarity.

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 description is one front-loaded sentence that efficiently summarizes the tool's scope and ends with a useful version tag. It has no fluff, though the middle is a list-like inventory of operations rather than a more structured overview. It earns high marks for conciseness.

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?

Given the very rich input schema—21 parameters, a required action enum, and per-action usage descriptions inside the schema—the high-level description works as an adequate overview. However, there is no output schema and no annotations, leaving return shapes and side effects unspecified, so the description alone would not be fully sufficient. The schema compensates enough to raise this above a 3.

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 in the input schema. The description itself adds no parameter-level meaning; it only restates operation categories. 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 opens with a resource ("IVA chat management") and enumerates concrete operations: create group chat, get/search/update/delete chats, forward messages, clear history, manage notifications, get P2P chat, get muted chats. This is clear and non-tautological, but it does not explicitly differentiate from siblings like iva_chat_messages or iva_chat_participants, so it stops short of a 5.

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 prose gives no guidance on when to choose this tool over its chat-focused siblings, nor does it state any exclusions. The 'use when' hints live only inside the action enum in the input schema, which is structured data rather than description content. An agent selecting between iva_chat and iva_chat_messages gets no tool-level direction from the description.

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?

With no annotations, the tool description carries the full burden of disclosing side effects, but it does not mention that recording, transfer, leave, or outgoing-call actions change call state or may be irreversible. The only destructive-action hint appears in the confirm parameter description, not in the tool description.

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 description is one compact, front-loaded sentence that communicates the full operation range plus a version tag. It is efficient and free of filler, though the dense semicolon list reads more like a catalog than a narrative.

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 16 actions, 9 parameters, nested objects, and no output schema, the high-level description is thin, and the schema does not specify which params are required per action. However, the detailed action enum and parameter descriptions cover much of the operational semantics, so the definition is minimally adequate with clear gaps.

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 description adds no parameter-level information, but schema description coverage is 100% and the action enum is richly explained. Nested-object descriptions such as callData: 'Start call data' are thin, yet the schema meets the high-coverage baseline, so a 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 names the resource (IVA chat calls) and enumerates the concrete operations: join/leave/hold, recording, screen sharing, transfer, DTMF, media state, and outgoing calls. This is specific enough to distinguish from sibling tools but it is a catalog rather than a single verb-purpose statement, so not a 5.

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?

There is no when-to-use guidance and no contrast with alternatives such as iva_chat or iva_conference. The description simply lists operations, leaving the agent to infer when this tool should be selected.

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?

No annotations are provided, so the description must carry behavioral disclosure alone. It merely lists operations and does not mention that several actions (delete, delete_multiple, remove_attachment) are destructive, nor does it describe authentication requirements, rate limits, pagination behavior, or response shape. The version string 'Clients API v2.28.12' adds little behavioral insight. The enumeration does imply mutation, but lacks the necessary consequences and caveats.

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 description is one compact sentence and a short version suffix, efficiently summarizing the tool's scope without unnecessary prose. The list of operations is front-loaded before the API version. It could be structured slightly better (for example grouping read vs write vs destructive actions), but it is appropriately concise.

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?

Given a complex 20-parameter polymorphic tool with no output schema and no annotations, the description is only an overview. The rich schema compensates for parameter documentation, but the description does not explain that the tool is an action dispatcher, which actions are destructive and require confirmation, or what kind of response to expect. It is adequate as a high-level entry point but not fully sufficient on its own.

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 structured schema already documents each parameter meaning. The tool description adds no extra parameter semantics beyond the schema. Per calibration baseline, with full schema coverage a score of 3 is appropriate: the description is not harmful but does not compensate for anything missing.

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 identifies the resource ('IVA chat messages') and lists the main operations: send/edit/delete/star messages, search attachments, get messages/changes/starred, typing notification, read receipt. It is not merely a tautology and gives an agent a useful overview. It does not explicitly contrast with siblings like iva_chat, but the focus on messages is reasonably distinctive.

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 prose description gives no guidance on when to choose this tool over alternatives such as iva_chat or iva_conference_chat. Some per-action usage hints (e.g., use 'send' when the user says 'отправь сообщение') exist inside the action enum, but those are structured schema content rather than the tool description. Without explicit when-to-use or when-not-to-use guidance, the agent is left to infer routing from the operation list.

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?

With no annotations, the description must carry the burden of behavioral disclosure. It only says the operations exist ('add and remove participants, update participant settings') but does not disclose that removals may be destructive, that confirmation may be required, or any side effects or permissions. This is a meaningful gap for a mutating 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?

The core sentence is concise and front-loaded with the action and resource. The trailing 'Clients API v2.28.12' adds marginal value and does not actively hurt, but it is not fully load-bearing.

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?

This is a 7-parameter tool with nested objects, no annotations, and no output schema, yet the description is only one short sentence. The schema covers parameter meanings, but the description does not explain operation-to-parameter relationships, confirmation requirements, or expected behavioral outcomes, leaving the agent to infer too much.

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 documents all parameters and the action enum. The description adds no parameter-level meaning beyond restating the high-level operations, so the baseline score 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 names a specific resource (IVA chat participants) and a concrete set of operations: add, remove, and update participant settings. This clearly distinguishes it from sibling tools like iva_conference_participants by scoping it to chat rooms.

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 phrase 'IVA chat participants' provides clear context that this tool is for chat-room participant management, which helps an agent choose it over conference-participant tools. However, it does not explicitly state when not to use it or name alternatives, so it stops short of full 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?

No annotations provided, so the description carries the full burden of behavioral disclosure. It lists operations but does not mention destructive-action confirmation behavior (despite a confirm parameter), side effects, permission requirements, or any consequences of the mutating actions. The tool is heavily mutative (create/update/delete/respond), yet the description gives no behavioral caveats.

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?

One efficient, front-loaded sentence that summarizes scope before listing operations. No filler words and the API version tag is useful context. Slight redundancy with the action enum, but as a summary it earns its place.

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?

This is a complex tool-12 distinct actions, 11 parameters, nested objects, no output schema, and no annotations-and the description is a single summary line. It does not explain action-parameter coupling, return behavior (relevant since there is no output schema), or the confirm/IVA_CONFIRM_DESTRUCTIVE flow for destructive actions. The rich action-enum descriptions compensate partially, but the description itself leaves major navigation gaps.

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 baseline is 3. The description adds only a high-level mapping of operations to the action enum, but the schema already documents each parameter in detail (including required conferenceData fields and UNIX ms format). The description does not go beyond the structured data.

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 clear verb+resource ('IVA conference management') and enumerates the operations it covers: create/get/update/delete conferences, schedule calculation, quick start, room creation, participants, invitations, free resources. This distinguishes it from non-conference siblings like iva_documents or iva_chat. However, it does not differentiate from specialized conference siblings (iva_conference_participants, iva_conference_session, iva_conference_media), leaving boundary ambiguity.

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 provides no when-to-use or when-not-to-use guidance and names no alternatives. The detailed per-action usage examples ('Use this when user says...') live in the action enum schema, not in the description, so the description field itself offers no routing help.

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?

With no annotations at all, the description carries the full burden of behavioral disclosure. It lists destructive operations like remove, remove_all, and moderate, but does not disclose side effects, confirmation requirements, whether changes are reversible, or what the returned data looks like.

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 description is a single compact sentence that front-loads the resource and lists operations efficiently. The trailing 'Clients API v2.28.12' is minor noise, but overall the structure is concise and scannable.

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?

This is a high-complexity tool with 17 parameters, 10 actions, nested objects, no output schema, and no annotations. The description does not explain which parameters apply to which action, how pagination works, what export_txt returns, or how destructive actions are confirmed. This leaves significant gaps for an agent to call 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?

Schema description coverage is 100%, so the baseline is 3. The tool description itself adds no parameter-level meaning beyond repeating the operation list, but the action enum in the schema provides detailed bilingual explanations for each operation.

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 identifies the resource as 'IVA conference chat messages' and enumerates the operations it supports: send, edit, remove, moderate, get, export, typing, and remove-all. It is clear and specific, though it does not explicitly differentiate itself from sibling tools like iva_chat_messages or iva_chat.

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?

No guidance is provided about when to use this tool versus alternatives. It does not mention prerequisites such as requiring a conferenceSessionId, nor does it explain which sibling tools should be used instead for non-conference chat scenarios.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It names destructive and state-changing operations like delete, move, stop, and update, but does not disclose side effects, confirmation requirements, permission needs, or any constraints. Similarly, the demo/video control operations imply session state changes but no behavioral context is given.

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 description is a single terse sentence that front-loads the domain name, but it is mostly a comma-separated rehash of categories already present in the action enum. The trailing 'Clients API v2.28.12' adds no operational value. Efficient in length, but not well structured for an agent to extract actionable guidance.

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?

This is a highly complex dispatcher tool with 14 parameters, 19 action enum values, nested objects, and no output schema, yet the description provides only a high-level summary. It does not map actions to required parameters, mention return behavior, or clarify prerequisites. An agent would need to rely almost entirely on the schema to invoke it 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?

Schema description coverage is 100%, so the parameter schema already documents every parameter individually. The description adds no additional meaning beyond the schema; it only lists operation categories. Baseline 3 is appropriate because the schema does the heavy lifting and the description does not compensate with extra context.

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 identifies the resource as 'IVA conference documents' and enumerates the main families of operations: CRUD/list/move, demo control, and page/path/upload queries. It is specific enough to distinguish the tool from generic iva_documents by conference scope, but it is a broad capability list rather than a single focused verb+resource statement.

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 provides no guidance on when to use this tool versus alternatives like iva_documents, iva_conference_media, or iva_file_resources. It does not state prerequisites, exclusions, or selection conditions, so an agent must infer applicability solely from the resource name and operation list.

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?

No annotations are provided, so the description must carry the behavioral burden. It names many mutating/destructive actions (delete, stop, update, answer) but does not disclose side effects, confirmation requirements, permissions, or operation-specific behavior; the confirm behavior is only mentioned in the schema, not in the description.

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 description is a compact single sentence that front-loads the resource and lists operations efficiently. The trailing 'Clients API v2.28.12' is marginally useful version context but not central to invocation.

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?

This is a high-complexity facade with 11 parameters, nested objects, many enum actions, and no output schema; the description does not explain how the action parameter dispatches behavior, what each operation returns, or how conferenceSessionId relates to it. An agent would need the schema and further inference to call it 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?

Schema description coverage is 100%, so the schema already explains all 11 parameters, including action enums and UUID meanings. The tool description adds no parameter-level detail beyond that, which matches the baseline for high schema coverage.

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 identifies a specific resource ('IVA conference inquiries (polls)') and enumerates precise operations (create, find, get, delete, update, start/stop, answers, export), so an agent can see what the tool does. It does not explicitly contrast with closely related siblings such as iva_conference_questionnaire, so it stops short of full differentiation.

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 no guidance about when to call this tool instead of a sibling or which action to choose for a given intent. It merely lists capabilities; no when/when-not or alternative conditions are stated.

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?

There are no annotations, so the description carries the full burden of behavioral disclosure. It lists actions but does not disclose the consequences of approving/rejecting participants, whether actions are reversible, permission requirements, or when the confirm parameter might be required for destructive actions. This is a significant gap for a mutating multi-action 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?

The description is a single compact sentence that front-loads the resource and then lists the operations clearly. The trailing 'Clients API v2.28.12' is low-value, but overall there is little wasted text and the structure is easy to scan.

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 schema covers parameter meanings, but not per-action parameter dependencies such as which actions require profileId versus conferenceSessionId, nor expected return values or side effects. With no output schema and no annotations, this brief description is insufficient for correctly invoking all seven actions in every situation.

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 all four parameters are already documented in the schema. The description stays appropriately high-level and adds no parameter-specific meaning, matching the baseline for fully covered schemas.

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 names the resource ('IVA conference lobby') and enumerates the specific operations: join/leave, get participants, and approve/reject individual or all requests. It is more specific than a tautology and helps distinguish this tool from the nearby conference/participant 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 description implies when to use the tool: when a caller needs to manage a conference lobby. However, it gives no explicit guidance about alternatives such as iva_conference_participants or iva_conference_session, nor does it state when to prefer this tool over those siblings.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only lists operations without explaining side effects, permissions, destructive actions, confirmation requirements, or response behavior. The mention of 'Clients API v2.28.12' is a version note, not behavioral transparency.

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 description is a single compact sentence that packs the full operation list with minimal waste. It uses a readable grouped structure (get/report/request/revoke/set). It could be slightly better structured as bullets, but for a 12-action tool it remains efficient and scannable.

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?

Given the high complexity — 12 parameters, nested objects, no annotations, no output schema — the description is too thin. It does not map parameters to actions, explain which operations are destructive or require confirmation, or describe expected outcomes. An agent could guess from parameter names, but the description leaves too much unstated.

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%, and the action parameter itself has detailed bilingual per-operation descriptions. The tool description adds no parameter semantics beyond what the schema already provides, so the baseline 3 applies. The nested 'Data' objects are vaguely described, but this is a schema limitation, not a description gap.

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 enumerates the tool's operations: get media/room info, report state, request/revoke attention, report equipment, and multiple settings. It identifies the resource domain ('IVA conference media') and distinguishes it from sibling tools by scope. However, because it is a multi-action tool, it lacks a single specific verb, so it doesn't reach a 5.

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 provides no guidance on when to use this tool versus the many conference-related siblings (iva_conference, iva_conference_session, iva_conference_presence_control, etc.). The domain is implied by the name and the operation list, but no exclusions or alternative references are given.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It lists many mutating actions (remove, disconect, cancel, stop) but does not state side effects, confirmation requirements, permissions, or response behavior. The names imply operations, but consequences of destructive actions are not disclosed in the description.

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 description is a single front-loaded sentence that lists the main operation groups and ends with a useful API version context. It is concise, but the long comma-separared list reads more like an enumeration than an explanation, so it does not quite reach the top tier.

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?

Given the tool's complexity (23 actions, 15 parameters, no annotations, no output schema), a one-line list of operations is not fully complete on its own. The rich schema action descriptions compensate substantially, but missing behavioral context around destructive operations, authentication, and return values leaves an agent under-informed for correct invocation in edge cases.

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%, and parameter descriptions already document each field and action-specific requirements (e.g., add requires conferenceSessionId and participants). The description adds no parameter-level meaning, which is acceptable at the baseline given full schema coverage.

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 identifies the resource ('IVA conference participants') and enumerates the operation categories (add/remove/find/get/disconnect, mute/unmute, hand up/down, DTMF, reactions, etc.), so an agent can tell what the tool manages. It does not explicitly name sibling tools to distinguish against, but 'conference participants' is a reasonably specific resource scope.

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 implies participant-level conference operations belong in this tool, and the schema's action enum adds triggered-use hints such as 'Use when user says выключи микрофон' and 'raise hand'. However, the tool-level description gives no explicit when-to-use vs alternatives guidance, no prerequisites, and no exclusions for neighboring conference tools.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the high-level actions but does not explain side effects, destructiveness of stop, permission requirements, state dependencies, or what happens to a conference when presence control starts or stops. This is minimal for a mutating control 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?

The description is a single, front-loaded sentence with no filler. It quickly conveys the tool's purpose and main actions. The version note is minor but not distracting. It could be slightly more informative without losing conciseness, but it is well-structured.

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?

This tool has six parameters, two nested objects, no output schema, and no annotations, yet the description offers no guidance on how the parameters relate to the actions, what startData or confirmData should contain, or which IDs are needed for each operation. An agent would struggle to construct a correct call beyond selecting the action enum value.

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 documents each parameter. The description adds no extra meaning about startData, confirmData, presenceControlId, or conferenceSessionId beyond what the schema provides. Baseline 3 is appropriate because 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?

The description clearly identifies the tool's domain ('conference presence control') and the three core operations: start, stop, and confirm attendance. It uses a specific resource and action set, which distinguishes it from sibling conference tools, though it does not explicitly contrast with any sibling.

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 no guidance on when to use this tool versus alternative conference tools, nor does it mention prerequisites, whether a conference session must already exist, or when start versus stop versus confirm should be invoked. No alternatives or exclusions are provided.

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?

With no annotations, the description carries the full burden of behavioral disclosure. It only indicates that 'get' is read-like and 'save_answers' is write-like, but does not explain side effects of saving, whether answers are overwritten, permission requirements, or the need for confirmation. 'Clients API v2.28.12' adds version context but no behavioral insight.

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 description is very concise and front-loaded with the core operations. The 'Clients API v2.28.12' sentence adds limited value, but the overall length is appropriate and easy to parse.

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 a mutating action, multiple parameters, nested objects, no annotations, and no output schema, the description is too thin. It omits behavioral effects, return information, and usage prerequisites, leaving the agent to rely entirely on the schema for operational context.

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 input schema already documents all four parameters, including the action enum, conferenceSessionId UUID, answersData, and confirm. The description adds no parameter-level meaning beyond what the schema provides, so the baseline score 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 concrete operations ('get questionnaire, save questionnaire answers') on a specific resource, making the tool's purpose clear at a glance. It does not explicitly differentiate from sibling tools like iva_conference_session or iva_conference_inquiry, but the resource name 'questionnaire' is specific enough to avoid major ambiguity.

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?

Usage context is implied rather than explicit: an agent can infer that this tool is for questionnaire read/write operations. However, the description gives no guidance on when to prefer this tool over related conference siblings, and it does not mention prerequisites such as needing a conferenceSessionId or when confirm is required.

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?

With no annotations provided, the description carries the full behavioral disclosure burden, but it only repeats the operation names. It does not mention side effects such as creating a registration or sending emails, nor does it explain prerequisites like a valid conferenceSessionId or the destructive-action confirm flag visible in the schema.

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 description is very short, front-loads the domain, and avoids redundancy. The 'Clients API v2.28.12' version note is peripheral rather than essential, but it does not harm clarity. It is concise rather than overly verbose.

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 five parameters, two unspecified nested objects, no output schema, and no annotations, so the description needed to explain data shapes and invocation context. It provides no information about payload requirements, expected registration/email flow, or response and error behavior. An agent might select the tool but cannot reliably invoke it 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?

Schema description coverage is 100%, and the action enum already provides detailed bilingual descriptions, so the baseline applies. The description adds no meaning beyond repeating the enum labels; nested objects such as emailData and registrationData remain unexplained in both description and 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?

The description identifies the exact resource (IVA conference self-registration) and lists concrete operations—register, check email, resend email—which map directly to the action enum. This clearly separates it from sibling conference tools such as iva_conference_participants or iva_conference_session.

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 implies usage by enumerating the supported self-service operations, so an agent can infer when to select it. However, it gives no explicit guidance about when to use this tool versus a sibling tool, and no exclusion conditions or alternative routing cues.

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?

There are no annotations, so the description carries the burden of disclosing behavioral traits, but it only lists operation categories. It does not mention destructive side effects, the confirm requirement for destructive operations, authentication prerequisites, or reversibility. The schema's 'confirm' parameter hints at confirmation behavior, but the description itself gives no behavioral transparency beyond stating the tool is for session management.

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 description is a single concise sentence that front-loads the tool's scope and avoids fluff. The trailing 'Clients API v2.28.12' provides useful version context. It is tight, though the long comma-separated category list is somewhat dense and could be structured more cleanly.

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 35 actions, 21 parameters, no annotations, and no output schema, so the description is far from sufficient as a standalone context source. It omits return-value behavior, pagination details, authentication scope beyond 'public info', and destructive-action safeguards. The action enum descriptions in the schema help, but the description itself leaves major contextual gaps for an agent deciding how to invoke the 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 the schema already documents all 21 parameters, including the action enum with detailed per-action semantics. The description adds no parameter-level meaning beyond what the schema provides. It also does not need to compensate because coverage is high, 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 specific verbs and a resource: 'get/find/update/delete sessions, join/leave, start/stop, timer control, recording, transcription, subtitling, media publication, invitations, public info.' This is clear about what the tool covers and distinguishes it as a session-management tool. It does not explicitly contrast with sibling tools like iva_conference_session_groups or iva_conference_media, but the operation list is specific enough to orient an agent.

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?

Usage guidance is largely implicit: the description lists categories of operations but does not say when to prefer this tool over alternatives such as iva_conference or iva_conference_media. However, the action enum descriptions inside the schema include explicit triggers like "Use when user says 'покажи встречи'" and "Use when user says 'войди в конференцию'", which provide usable selection guidance for individual actions.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It names mutating operations such as remove and deactivate, but does not explain destructive consequences, required permissions, confirmation behavior, or session-wide effects. The confirm parameter exists in the schema, yet the description never mentions when confirmation is needed.

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 description is a single compact sentence that front-loads the resource name and lists the main operations. It is appropriately sized, though the version suffix 'Clients API v2.28.12' adds limited value and the dense listing could be slightly more structured.

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?

This is a high-complexity tool with nine parameters, seven actions, nested objects, and no output schema, yet the description provides only a one-line overview. It misses operation-specific expectations, return behavior, and practical effects of destructive actions, making it incomplete for safe invocation.

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%, and the action enum values already describe each operation in detail. The tool description repeats operation names but adds no parameter-level meaning beyond the schema, so it meets the baseline without compensating further.

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 identifies a specific resource (IVA conference session groups) and enumerates the supported operations: create, activate, deactivate, remove, extend duration, move participants, and get. It clearly states what the tool does, though it does not explicitly differentiate it from related sibling tools such as iva_conference_participants or iva_conference_session.

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?

No guidance is given on when to use this tool versus the many conference-related sibling tools, nor does it describe prerequisites or contexts for each action. The operation list implies group-management usage, but the agent is left to infer appropriate scenarios.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not state whether operations are read-only, whether exports create files or return data, whether any actions require confirmation, or what side effects occur. The schema reveals a 'confirm' parameter hinting at destructive actions, but the description never addresses this, leaving the agent without critical behavioral context.

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 description is relatively short and front-loads the tool's purpose. However, it is a single run-on-style list rather than structured guidance, and the final clause 'Clients API v2.28.12' does not earn its place for an agent selecting or invoking the tool. It is concise but not optimally structured.

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?

This is a complex dispatcher with 17 actions and 11 parameters, no annotations, and no output schema. The description does not explain how to select among the many actions, which parameters are required for each action, how date ranges and pagination work, or what the export operations return. The schema's action descriptions help, but the top-level description leaves too much unspecified for such a multifaceted 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 the baseline is 3: all parameters already have descriptions, and the action enum has detailed bilingual explanations for each operation. The top-level description adds no parameter-level meaning beyond loosely naming categories like 'export to CSV' and 'sessions statistics aggregation.' This is acceptable because 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?

The description clearly identifies the tool's domain: conference statistics, including session/participant stats, activity, aggregation, and CSV export. It is recognizable as distinct from sibling tools like iva_conference_session or iva_conference_participants because it explicitly centers on statistics rather than session management or participant management. However, it does not name a single verb+resource, instead summarizing a multi-action dispatcher, and the trailing 'Clients API v2.28.12' adds noise.

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?

There is no guidance about when to use this tool versus the many sibling conference tools, nor any mention of alternatives or exclusions. The description implies a statistics-gathering role but does not state conditions like 'use for analytics/reporting' or 'use iva_conference_session for session management.' The detailed per-action guidance lives in the schema, not in the description.

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?

No annotations are present, so the description carries the burden of behavioral disclosure, but it only restates the operation names already in the schema enum. It does not mention side effects of setting a default, confirmation requirements for deletes, permission needs, or whether changes are reversible. The destructive 'delete' action is visible in the schema, so the description adds no new behavioral context.

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 description is a single compact sentence that front-loads the resource and operation set, making it scannable. The trailing 'Clients API v2.28.12' is low-value but not harmful, and the core content has no wasted words.

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 schema richly documents parameters and enumerates actions, but the description omits action-to-parameter relationships (e.g., create/update need templateData, get/delete need conferenceTemplateId) and gives no info about return values. Given the tool's complexity and lack of output schema, the description is adequate but leaves some contextual work to the agent.

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 parameter details are fully documented in the schema. The description adds no extra meaning about parameters such as templateData or conferenceTemplateId, but it also does not need to repeat them. Baseline 3 is appropriate because structured data already 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?

The description names the exact resource ('IVA conference templates') and enumerates all six operations: list/create/get/delete/update and set as default. This clearly distinguishes the tool from sibling conference tools, which focus on sessions, media, chat, or participants rather than template management.

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 makes the tool's scope explicit by listing the full set of supported template operations, so an agent can infer that any conference-template management task belongs here. It does not explicitly name alternatives or give exclusionary guidance, but the resource name and action list provide clear context.

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?

There are no annotations, so the description carries the full burden of behavioral disclosure. It does not disclose side effects for destructive actions like remove, reject_invitation, or update, nor does it mention confirmation behavior, permissions, or rate limits. The action names imply mutation, but the description adds no behavioral context beyond what is obvious from the schema.

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 description is compact and front-loaded with the domain, but it is an unstructured list that partially duplicates the action enum. It also introduces 'search' even though no search action exists in the enum, which is slightly misleading. The trailing API version adds little value.

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?

This is a high-complexity dispatcher tool with 12 parameters, 12 actions, nested objects, and no output schema. The description does not explain which parameters apply to which actions, what the return values look like, or how pagination and date filters work. The schema helps, but the description leaves important contextual gaps for an agent selecting and invoking 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?

Schema description coverage is 100%, and the action enum has detailed per-action descriptions, so the schema already documents parameters well. The tool description adds no parameter-level meaning, which is acceptable here since the schema covers it. Baseline 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 identifies the resource ('IVA contacts') and enumerates the main operations (get, changes, presences, invitations, invite, reject, remove, update, create note), so an agent can tell this is a contacts-management dispatcher. It is distinct from sibling tools by domain, though it does not explicitly differentiate itself from related tools like iva_interlocutors.

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?

No guidance is given about when to use this tool versus any sibling or alternative. The description lists operations but does not state selection criteria, prerequisites, or which sibling tools cover related but different domains.

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?

No annotations are present, so the description carries the full burden of behavioral disclosure. It identifies register/deregister as the operations but does not state that deregistration is destructive, whether confirmation may be required, or what side effects or prerequisites exist. The confirm parameter is only documented in the schema, not in the description.

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 main sentence is short and front-loaded with the key purpose. The trailing 'Clients API v2.28.12' is minor extra context, not harmful, but it does not earn its place as strongly as the core sentence.

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 five parameters, nested deviceData, and no output schema, the description provides only a high-level summary. It does not clarify which parameters apply to register versus deregister, what deviceData should contain, or which operations need confirmation, so an agent could still struggle to invoke it 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?

Schema description coverage is 100%, so the structured schema already documents action, confirm, deviceId, profileId, and deviceData. The description adds no extra meaning beyond the schema, which places it at the baseline of 3 rather than higher.

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 clear resource ('user devices') and specific operations ('register and deregister'), so an agent can identify the tool's core function. It does not explicitly contrast it with sibling tools, but none of the listed siblings obviously overlaps with device registration management.

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 no guidance on when to choose this tool over alternatives, nor does it mention prerequisites or conditions for registration versus deregistration. The action enum hints at the two flows, but the description itself provides no decision context.

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?

With no annotations, the description carries the full burden of behavioral disclosure. It mentions delete operations, which imply mutation, but does not disclose that deletes are destructive, irreversible, or may require confirmation. There is no mention of authentication, side effects, or return behavior.

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 description is a single front-loaded sentence that states scope and operations without redundancy. The API version is a minor extra but does not hurt clarity or structure.

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?

Despite having no annotations and no output schema, the description is very terse for a multi-action tool with destructive operations. It omits what the tool returns, when confirmation is needed, and how it relates to other document tools. The schema covers parameters, but the description does not provide enough operational context for an agent to invoke the tool confidently.

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%, and the schema already documents all six parameters including the action enum values and the confirm flag semantics. The tool description adds only a high-level summary of operations, so it does not meaningfully improve parameter understanding beyond the 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?

The description names a clear resource ('IVA user documents') and specific operations: convert, delete single/multiple, and list converted pages. This gives an agent enough to identify the tool's basic function, though it does not explicitly distinguish itself from sibling tools like iva_conference_documents.

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?

No guidance is given about when to use this tool versus alternatives, and no exclusions or prerequisites are mentioned. The phrase 'IVA user documents' implies a scope, but the description does not state conditions like 'for user-level documents, not conference documents'.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only lists operation names and does not mention side effects, prerequisites, permissions, destructiveness, idempotency, or what happens during scanning subscriptions. The existence of a 'confirm' parameter hints at destructive actions, but the description does not address this.

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 description is a single compact sentence that front-loads the tool's purpose and enumerates its operations without extraneous detail. The version reference is minor but not distracting.

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?

This is a multi-action tool with six parameters, nested objects, no output schema, and no annotations. The description does not explain the create-then-upload flow, required parameters per action, meaning of the nested objects, or expected return values. The action enum helps but still leaves important invocation context uncovered.

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 documents the parameters and the action enum contains detailed per-action descriptions. The tool description adds little beyond the schema, and opaque nested objects like scanData and resourcesInfo remain unexplained, but the high schema coverage justifies the baseline score.

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 identifies the tool as handling IVA file resources and enumerates its operations: create, download/upload, get info, and subscribe to scanning status. This is specific enough to distinguish it from the many sibling tools focused on chat, conferences, documents, and profiles, though it does not explicitly contrast an alternative.

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 no guidance on when to use this tool versus related tools such as iva_documents or other resource-oriented siblings. It lists capabilities but provides no conditional context, exclusions, or pointers to alternatives.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It lists operations but does not explain side effects, whether presence subscriptions persist, how to unsubscribe, permission requirements, or any destructive or stateful behavior associated with the actions.

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 description is a single compact sentence that front-loads the operation list and includes the API version at the end. There is no filler or repetition, though the action list is slightly redundant with the schema's enum.

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 action enum in the schema provides helpful per-operation details, making the tool somewhat self-explanatory. However, with no output schema, no annotations, and a vague findCriteria object, the description leaves return values, subscription lifecycle, and nested criteria structure under-specified.

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%, with the action enum providing detailed per-value explanations and parameter descriptions. The prose description restates the action names but does not add meaningful parameter semantics 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 names the resource (IVA interlocutors) and enumerates concrete operations: find by contact/ldap/profile/profileIds, find interlocutors, get types, and subscribe to presence. This makes the tool's purpose clear, though it does not explicitly distinguish it from sibling tools like iva_contacts or iva_profile.

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 summarizes available actions but provides no guidance on when to use this tool versus alternatives such as iva_contacts, iva_profile, or iva_chat. It also omits prerequisites and any exclusion criteria, leaving usage context entirely to inference.

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?

No annotations are provided, so the description carries the full behavioral disclosure burden. It only adds a security exclusion for password/recovery actions and the API version; it does not disclose that actions like delete_call_forwarding mutate state, require confirmation, or may be irreversible. This is a significant gap for a tool with destructive actions.

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 description is front-loaded with a compact capability summary and closes with a useful security note. It is short, scannable, and every sentence contributes to understanding the tool's scope.

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 8 parameters and 13 actions, the schema carries rich detail including per-action usage hints and natural-language examples. The description provides the umbrella scope and the security boundary. The main gap is the absence of return-value info, but that is partially mitigated by the intuitive nature of the get/update operations.

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 baseline is 3. The top-level description adds no parameter-level detail beyond naming the capability areas, while the schema already provides detailed action descriptions, enum values, types, and parameter purposes.

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 identifies the tool as IVA user profile management and enumerates its domains: profile get/update, call forwarding, disk utilization, notifications, and subscriptions. It is specific enough to distinguish from sibling tools like iva_user_session or iva_documents, though it relies on the broad noun 'management' rather than a single precise verb+resource statement.

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 implies usage for profile-related tasks and lists the covered areas, which gives an agent a basis for tool selection. However, it does not explicitly state when to use this tool versus sibling tools, nor does it provide exclusion guidance beyond the password/recovery security note.

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?

No annotations are provided, so the description carries the full behavioral burden. It lists mutating operations such as start, stop, request, and respond, and it notes the API version, but it does not explain side effects, permission requirements, the remote-control handshake flow, or when destructive confirmation is needed.

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 description is a single compact sentence plus a version note, with no filler or repetition. Every phrase contributes to identifying the tool's operation set, and the key capabilities are 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?

For a tool with 8 parameters, nested objects, no output schema, and no behavioral annotations, the description is minimally viable but incomplete. It omits the remote-control flow, the required contents of nested data objects, and expected outcomes, although the detailed action enum partially compensates.

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%, including detailed per-operation text in the action enum, so the schema already explains most parameters. The prose description adds no parameter-level meaning, and nested objects like batchData, startData, and controlData remain only generically described, 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?

The description names a concrete resource (IVA screenshare) and enumerates its operations: start/stop web or VNC screen sharing, and request/respond/stop remote control, plus batch respond. This is specific and not a tautology, though it does not explicitly differentiate itself from sibling tools like iva_conference_media.

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 provides no when-to-use guidance, prerequisites, or exclusions relative to the many sibling IVA tools. The only usage hints are implicit in the operation names and the action enum inside the schema, so an agent is left to infer when this tool should be selected.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It lists actions like 'SMS approval, crash report, mail to support' but does not disclose that these are side-effect operations, whether authentication is required, or any consequences such as sending emails or confirming destructive actions. The behavioral detail exists only in the input schema, not in the description.

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 description is compact and front-loaded with the module name, followed by a comma-separated list of capabilities. It is efficient and scannable, though the phrase 'system info' is repeated and the structure is more of a tag list than a complete sentence.

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?

This is a high-complexity aggregate tool with 10 possible actions, multiple optional parameters, nested objects, and no output schema. The description is only a one-line capability list and does not explain return values, required inputs for nested objects like smsData and mailData, or operation-specific behavior. The schema helps, but the description alone is not sufficient for an agent to call all variants confidently.

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%, and the action enum provides meaningful descriptions for each operation, including the confirm destructive-action flag and the crash-report file parameter. The description itself adds little parameter-level meaning, but the schema already covers this dimension adequately.

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 the tool's domain as 'IVA system info' and enumerates concrete capabilities: system info, media info, ICE servers, layouts, broadcast notifications, SMS approval, crash report, mail to support, and client applications. It is clear that this is the system-level utility tool, though it lacks a single strong verb and is broader than a typical single-purpose tool.

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 no guidance on when to use this tool versus alternatives such as iva_conference_media, iva_file_resources, or iva_profile. The scope is implied by the list of system-level operations, but there are no explicit when-to-use or when-not-to-use instructions.

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?

With no annotations, the description carries the disclosure burden; it adds a useful security note that login and 2FA actions are excluded and authentication is automatic. It does not disclose side effects such as logout ending the session or set_session_state mutating presence, although those details appear in the schema's action enum.

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 description is short and front-loaded with the key operation list. The security note is relevant and concise, and there is little wasted text apart from the minor 'Clients API v2.28.12' fragment.

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 schema's action enum provides detailed descriptions of each operation, including effects and examples, and all four parameters are documented. Description plus schema together give an agent enough context to invoke the tool correctly, though there is no output schema or return-format note for session info.

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 baseline is 3. The tool description does not add parameter-level detail beyond naming operation areas; the schema already documents action, confirm, providerId, and sessionState.

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 opens with 'IVA user session management' and lists the concrete operation areas: logout, session info, guest login, session state, and login URL. This makes the tool's scope clear, though it lacks a single imperative verb and does not explicitly contrast with sibling tools.

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 implies this tool is for session-related actions and explicitly excludes login/2FA, explaining that authentication is handled automatically via IVA_LOGIN/IVA_PASSWORD environment variables. However, it does not state when to prefer this tool over sibling tools or provide condition-based usage guidance beyond the authentication exclusion.

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?

With no annotations provided, the description carries the full behavioral burden. It conveys a state-mutating, potentially destructive profile through verbs like add/delete/clear/copy, stop-demo, and undo, which is genuinely useful for an agent deciding whether invocation is safe. However, it does not disclose side effects such as demonstration actions being shown to participants, the irreversible nature of deletes, or any confirmation gating — those details appear only in the action enum and the confirm parameter description, not in the main description.

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?

A single dense sentence enumerates all 21 operations with virtually no fluff, and the domain ('IVA whiteboard') is front-loaded before the operation list. The 'Clients API v2.28.12' suffix is a minor oddity but supplies version context in one short phrase. It is appropriately sized for a multi-action dispatcher tool where a verbose explanation would hurt usability.

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?

This is a high-complexity tool: 21 actions, 17 parameters with nested objects, no output schema, and no annotations. The description covers the action space at summary level but does not address return values (despite the absent output schema) or side effects, and does not map which parameters apply to which actions. The schema's action enum descriptions compensate substantially, but the overall definition leans heavily on the schema rather than the description.

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% — every one of the 17 parameters is documented — so the baseline is 3 and the description need not compensate. The description names parameter families (cursor, demo state, books, pages) but adds no semantic detail beyond the schema. The action parameter's enum descriptions carry the real per-action parameter meaning, and the tool description does not extend or clarify it.

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 uses specific verb+resource pairs: 'start/stop demonstration', 'manage books and pages (add/delete/update/clear/copy/reorder)', 'export to PNG', 'undo', 'save change', and 'update cursor/demo state'. It clearly distinguishes iva_whiteboard from all 28 sibling tools, none of which cover whiteboard functionality. The final version stamp 'Clients API v2.28.12' adds useful provenance context and makes the tool's scope immediately evident.

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?

Usage context is implied through the enumerated operation families — demonstration control, book/page management, export, undo/save — and the sibling set makes it evident this is the only whiteboard entry point. However, there is no explicit when-to-use guidance, no exclusions, and no statement about when a sibling tool would be the better choice. The per-action usage requirements (e.g., 'start_demo Requires whiteboardState: {pageId, left, top, right, bottom}') live in the action enum descriptions inside the schema, not in the tool description itself.

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