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

Annotations indicate mutation (readOnlyHint=false) and open-world effects (openWorldHint=true). The description adds important behavioral details: the Premium requirement and the specific timeframes for future mode (25 minutes). However, it does not explain if the effect is reversible or how long past mode changes last.

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 highly concise: two sentences covering the core action, parameters, and a key constraint (Premium). Every sentence earns its place with no unnecessary 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?

For a simple mutation tool with two booleans and no output schema, the description covers the main functionality and an important error condition. Minor gaps exist around permanence and future mode toggling, but overall it is sufficiently complete given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear parameter descriptions, so baseline is 3. The tool description restates the parameter purposes in plain language but does not add significant semantic value 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?

Description clearly states the tool hides story views, specifying two modes (retroactively for past views and for the next 25 minutes for future views). It also mentions the Premium requirement, which distinguishes it from many other story-related sibling tools that handle sending, deleting, or reading stories.

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 context for when to use the tool (to hide story views) but does not explicitly mention when not to use it or compare it to alternatives like privacy settings or other story tools. No exclusions or alternatives 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?

Annotations indicate a write operation (readOnlyHint=false) with potential side effects (openWorldHint=true). Description adds no further behavioral details beyond stating the action, such as side effects or prerequisites.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the action. Every word adds value, no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Lacks information about return values (no output schema) and does not clarify parameter usage nuances (e.g., userId can be username). Considering the tool's simplicity and annotation coverage, it is minimally adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all parameters. Description does not add additional meaning or usage notes for parameters like 'userId' or 'phone' beyond what is in 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?

Description clearly states the action ('Add a user to your Telegram contacts') and provides a specific use case ('accept contact requests from non-contacts'). This distinguishes it from sibling tools like telegram-send-contact or telegram-get-contacts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells when to use ('use this to accept contact requests from non-contacts'). While it doesn't list alternatives, the context makes it clear that this is for adding contacts specifically.

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

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

The description adds the constraint that basic groups are not supported and the permission requirement, which are useful behavioral traits beyond the annotations' readOnlyHint=false and openWorldHint=true. However, it does not detail side effects, error conditions, or state changes.

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 extremely concise: two sentences, no redundant words, and captures the core purpose and a key requirement efficiently.

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 simplicity (3 params, no output schema), the description covers the main aspects: action, supported chat types, and permission needed. It lacks details on idempotency or error conditions but is largely sufficient for accurate 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?

The input schema already provides full descriptions for all three parameters (100% coverage), so the description adds minimal additional semantic value, only clarifying the pending state of requests.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action (approve or deny a pending join request), the target resource (supergroup or channel), and a critical constraint (basic groups not supported). This distinguishes it from sibling tools like kick-user or invite-to-group.

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 mentions that admin with invite_users permission is required, which gives usage context, but it does not explicitly compare to alternatives or state when not to use this tool relative to sibling 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?

Annotations already indicate it's a write operation (readOnlyHint=false). The description adds context ('moves to/from the Archive folder') but does not disclose potential side effects like notification suppression or permission requirements.

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?

Single sentence of 15 words, front-loaded with action, 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?

For a simple boolean toggle with fully described parameters, the description adequately explains the basic action. However, it lacks explanation of effects on chat visibility or unread state, which might be relevant.

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 covers all parameters with descriptions (100% coverage). The description adds no additional parameter meaning beyond what's already in 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 clearly states the verb (archive/unarchive), resource (Telegram dialog), and effect (moves to/from Archive folder). It distinguishes from all sibling tools, none of which mention archive.

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 on when to use this tool versus alternatives. It does not mention prerequisites (e.g., being a member of the chat) or scenarios where archiving is inappropriate.

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

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

Annotations already mark as write operation. Description adds permanence detail but omits required permissions, side effects (user removal from group), and whether it purges message history. openWorldHint true suggests unstated effects.

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?

Single sentence, 11 words, immediately conveys action and scope. No redundant or extraneous information.

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?

Simple tool with no output schema, but description could mention admin permissions requirement and that ban is only for supergroups/channels. Lacks mention of reversal (unban). Adequate but not thorough.

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 covers both parameters with descriptions. Tool description does not add format details (e.g., username vs numeric ID), so no extra value beyond schema. Baseline 3 due to 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?

Description clearly states verb 'ban', resource 'user', and context 'supergroup or channel' with permanence. Effectively distinguishes from sibling tools like 'kick' and 'unban'.

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?

Indicates permament ban but does not explicitly guide when to use versus alternatives like 'telegram-kick-user' or 'telegram-block-user'. No prerequisites or exclusion criteria 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?

Description adds the behavioral effect 'Blocked users cannot send you messages', which supplements annotations (readOnlyHint=false, openWorldHint=true). However, it does not mention reversibility via unblock, or any side effects beyond blocking messages.

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?

Extremely concise at two sentences with no unnecessary words. Could be slightly more informative without losing 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?

Tool is simple (one param, no output schema) and description covers the basic action. However, it lacks guidance on parameter format, user existence requirements, or how it interacts with other states (e.g., already blocked).

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?

Input schema provides 100% coverage with description 'User ID or username to block'. The description adds no extra meaning beyond that. 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?

Description clearly states 'Block a Telegram user' with a specific verb and resource. It distinguishes from siblings like ban-user and kick-user through the word 'block' and the effect 'cannot send you messages', but does not explicitly differentiate.

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 on when to use this tool versus alternatives like telegram-ban-user or telegram-kick-user. The description only states the effect without context on prerequisites or exclusion 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?

Annotations indicate destructive action. The description adds behavioral context: two modes of operation and the safeguard of confirmAllChats. It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, no extraneous words. Every sentence contributes essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with no output schema, the description covers all behaviors: single chat, all chats, and the confirmAllChats requirement. No 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 coverage is 100%, and the description adds value by clarifying that confirmAllChats is required when chatId is omitted, and that chatId accepts username as well.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Delete saved message drafts' with a specific verb and resource. It distinguishes between single-chat and all-chats usage, which differentiates it from siblings like telegram-save-draft.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explains when to use chatId for a single chat and when to omit it for all chats, explicitly noting that confirmAllChats must be true for bulk deletion. No explicit 'when not to use' but 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?

Annotations indicate readOnlyHint=false and openWorldHint=true. The description adds context about the specific action and scope but does not disclose additional behavioral traits (e.g., side effects, permissions). With annotations present, the description is adequate.

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 sentence that efficiently communicates the tool's purpose without any extraneous 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?

Given the tool has no parameters and no output schema, the description fully explains what the tool does. No additional information is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, and schema coverage is 100%. The description adds no parameter information, but none is needed. Baseline 4 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 clearly states the action ('clear') and the specific resource ('your recently-used emoji status list'). It distinguishes itself from sibling tools like 'set-emoji-status' by focusing on the 'recent' section.

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 the use case (clearing recent emoji statuses) but does not explicitly provide when-to-use or when-not-to-use guidance. However, the context is clear enough for an agent to select this tool over others.

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?

Discloses the irreversible nature of the operation. Annotations indicate non-read-only, and description adds the key behavioral fact that reopening is impossible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short, direct sentences with no unnecessary information. Every word adds 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?

Given the simple operation (close poll) with only two parameters and no output schema, the description is fully complete. It covers purpose, irreversibility, and need for chat and message IDs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and parameters are well-described in the schema. Description adds no additional detail beyond what schema 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 uses specific verb 'Close' and resource 'poll', clearly stating the action and its permanent nature. It distinguishes from siblings like vote-poll and create-poll.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states it is a one-way operation and that closed polls cannot be reopened, providing clear guidance on when to use and not use. Does not explicitly name alternatives but contextually sufficient.

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

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

Annotations indicate a write operation (readOnlyHint=false) and open-world hint. The description adds context by specifying the link format (t.me/m/...) and that it pre-fills a message, which is beyond what annotations provide.

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 two sentences, front-loaded with the core action, and includes essential detail without any fluff. Every sentence 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?

For a simple creation tool with 3 parameters, the description is fairly complete: it specifies the output fields, the prerequisite, and the link type. It lacks error or limitation details, but that's acceptable given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed descriptions for all 3 parameters. The description does not add new parameter meaning but mentions return fields, which is helpful but not about parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'create' and the resource 'Telegram Business chat link', specifying it's a deep-link type. It is distinct from sibling tools like telegram-create-invite-link or telegram-edit-business-chat-link.

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 mentions the prerequisite 'Requires Telegram Business subscription' but does not provide explicit guidance on when to use this tool versus alternatives like telegram-create-invite-link or telegram-edit-business-chat-link.

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

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

Annotations indicate this is a write operation (readOnlyHint=false) with unknown output structure (openWorldHint=true). The description adds behavioral details: returns the new folder ID and constrains emoticon to a single emoji character. It does not cover all potential side effects, but given annotations, it provides sufficient additional 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 three sentences, each delivering essential information: primary action and return value, two usage modes, and a constraint. No unnecessary words or repetition. Highly efficient.

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 (13 parameters, no output schema), the description covers the core creation logic, two key parameter groups, and a notable constraint. It lacks guidance on parameter interaction (e.g., mixing flags and includePeers) but is otherwise adequate for a selective 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?

While the schema describes all 13 parameters individually, the description adds semantic grouping: 'type flags to auto-include entire categories' vs. 'list specific chats in includePeers'. It also adds the constraint that emoticon must be a single emoji character, which is not fully captured in the schema's maxLength=2 description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a new Telegram chat folder and returns its ID. It distinguishes from related sibling tools like telegram-get-chat-folders, telegram-edit-folder, telegram-delete-folder by focusing on creation and mentioning specific usage patterns (type flags vs. includePeers).

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 guidance on two main usage patterns: using type flags for auto-including categories or listing specific chats in includePeers. It does not explicitly contrast with other folder tools or explain when to use this over editing, but the context of sibling tool names makes it reasonably clear.

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

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

Annotations indicate write operation (readOnlyHint=false) and open world (openWorldHint=true). Description adds the fact that it can create either a group or supergroup based on the supergroup parameter, providing some behavioral context beyond annotations. However, it omits important traits like rate limits or what happens on duplicate attempts.

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?

Single sentence, no redundant words, effectively conveys the core action. Perfectly concise for the information provided.

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 creation tool with 5 parameters and no output schema, the description lacks essential context: no mention of return value (e.g., created group ID), no explanation of supergroup vs group differences, and no side effects. The agent would be underinformed for proper 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?

Input schema has 100% description coverage for all 5 parameters, so schema already documents each parameter's purpose. The description adds no extra meaning beyond the schema, resulting in 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?

Description states 'Create a new Telegram group or supergroup' with a specific verb and resource, clearly distinguishing this tool from siblings like telegram-invite-to-group (adding to existing) and telegram-edit-group (modifying). The purpose is unambiguous.

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 on when to use this tool vs alternatives (e.g., when to choose group vs supergroup, or prerequisites like login). The description assumes basic knowledge, leaving the agent to infer usage 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?

Description only states 'create', which aligns with readOnlyHint=false (write operation). However, it does not disclose any additional behavioral traits, such as the need for admin rights, rate limits, or whether the link is automatically active. The openWorldHint=true annotation suggests possible side effects, but these are not explained.

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?

Single sentence of 10 words, front-loaded and efficient. No wasted words, but could be slightly longer to include essential guidance without losing 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?

For a creation tool with 5 parameters and no output schema, the description is too minimal. It omits what the tool returns (the invite link), prerequisites (e.g., must be admin), and how it interacts with related tools. Siblings indicate a rich domain, but this description does not provide sufficient context for correct use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and each parameter already has a clear description. The tool description adds no additional meaning beyond what is in the schema, so 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?

Clear verb and resource: 'Create a new invite link for a group or channel'. However, it does not distinguish from sibling like 'telegram-create-business-chat-link', which is a similar operation for business chats.

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 on when to use this tool vs alternatives. Siblings include 'telegram-revoke-invite-link', 'telegram-edit-business-chat-link', and 'telegram-get-invite-links', but the description provides no context for choosing this tool.

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

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

Annotations already indicate non-read-only (readOnlyHint=false) and open-world side effects (openWorldHint=true). The description adds that the poll can be multiple choice or quiz mode, which is useful context beyond annotations. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, short sentence that immediately conveys the tool's purpose. It is concise and front-loaded, with no unnecessary words or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 6 parameters (3 required) and no output schema. The description is minimal and does not mention prerequisites (e.g., bot permissions), error handling, or what the tool returns. While the schema covers parameters, the lack of output schema means the agent has no information about the return value or confirmation of success.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all 6 parameters. The description adds little beyond the schema, merely mentioning 'multiple choice or quiz mode' which is covered by the quiz and multipleChoice parameters. The description does not further clarify parameter usage or relationships.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Create a poll in a Telegram chat (multiple choice or quiz mode)', specifying the verb (create), resource (poll), and scope (in a Telegram chat) with mode differentiation. This distinguishes it from sibling tools like close-poll, vote-poll, and get-poll-results.

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 (to create a poll) but does not provide explicit guidance on when not to use it or mention alternatives. For example, it doesn't suggest using vote-poll or get-poll-results for other poll-related actions. No when-not or alternative hints 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?

Annotations already indicate readOnlyHint=false and openWorldHint=true, aligning with the write operation. The description adds the behavioral trait that it targets a forum-enabled supergroup, but no further details (e.g., failure behavior, limits).

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, well-structured sentence with no wasted words. It front-loads the action and context.

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 simple creation tool with no output schema, the description covers the essential purpose and prerequisites. However, it lacks information on error scenarios and what the result is, which would be helpful.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with each parameter described adequately. The tool description adds no extra meaning beyond the schema, so 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 clearly states the verb 'create', the resource 'forum topic', and the context 'forum-enabled supergroup'. It distinguishes from siblings like telegram-create-group (creates a group) and telegram-delete-topic / telegram-edit-topic.

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 (e.g., telegram-create-group) or what prerequisites are needed beyond stating 'forum-enabled supergroup'. No exclusions or context 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?

Annotations indicate readOnlyHint=false (write operation) and openWorldHint=true (side effects possible). The description adds the subscription requirement but does not disclose additional behavioral traits like irreversibility, immediate invalidation of link, or any cascading effects. With annotations providing partial transparency, the description adds modest context but not enough for a higher score.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first states action and method, second adds requirement. Extremely concise with no extraneous information. Front-loaded with the core purpose.

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 simple delete operation with one parameter, the description is mostly complete. It lacks mention of return value or success behavior, but given no output schema, this is a minor gap. The openWorldHint annotation suggests side effects, which are not explained, keeping it from a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and describes the 'slug' parameter with format hint. The description reuses 'by its slug', adding no new semantic depth beyond the schema. Baseline 3 for high 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 states the action (delete), resource (Telegram Business chat link), method (by slug), and a prerequisite (requires Telegram Business subscription). It distinguishes from sibling tools like create-business-chat-link, edit-business-chat-link, and get-business-chat-links.

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 a clear prerequisite (Telegram Business subscription) and context (by slug), but does not explicitly state when not to use this tool or name alternative tools. However, given the specific delete action, the usage is reasonably implied.

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

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

Annotations already indicate destructiveHint=true, so the description adds the privilege requirement. It does not elaborate on other behaviors like reversibility or side effects. With annotations present, the added value is moderate.

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 minimal: two sentences with no wasted words. All information is essential and 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 simple delete operation with two parameters and annotations covering destructive behavior, the description is sufficiently complete. It includes the crucial privilege requirement. Lacks info on return value, but output schema is absent and context is adequate.

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 description adds no additional meaning beyond the schema. The two parameters are well-documented in the schema, so the description is adequate but not enhanced.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Remove a fact-check annotation' using a specific verb ('Remove') and resource ('fact-check annotation'). It distinguishes from sibling tools like telegram-edit-fact-check and telegram-get-fact-check.

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 mentions a prerequisite ('Requires fact-checker privileges') but does not explicitly state when to use it vs alternatives or provide exclusion criteria. The usage context is implied by the name and privilege requirement.

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

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

The description discloses important behavioral traits beyond annotations: chats inside are not deleted and system folders cannot be deleted. Annotations indicate mutation (readOnlyHint=false) and potential side effects (openWorldHint=true), which align with the description. No contradictions.

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 two sentences: the first states the core action, the second provides crucial behavioral details and restrictions. It is concise, front-loaded, and every sentence adds 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?

Given one parameter, no output schema, and annotations that indicate mutation, the description completely covers what the tool does, its side effects on chats, and its limitations. No additional information is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers the single parameter 'id' with a description 'Folder ID to delete (≥ 2)'. The description does not add extra meaning beyond the schema, which already provides full coverage (100%). 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 clearly states the action (delete a Telegram chat folder by ID) and specifies what happens to chats inside (not deleted) and which folders cannot be deleted (system folders 0 and 1). It distinguishes from sibling tools like create-folder, edit-folder, etc.

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 clear context for when to use the tool (delete a folder) and when not to (system folders). However, it does not explicitly mention alternatives, but the context is sufficient for an AI agent.

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

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

Annotations already set destructiveHint=true, so the description doesn't need to state it's destructive. However, it adds no additional behavioral context (e.g., irreversible, requires permissions, limits on batch size).

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?

Single sentence, no fluff, front-loaded. Could add more context without much length, but current is efficient.

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 2 required params, 100% schema coverage, and no output schema, the description is minimally complete. Lacks usage guidelines and behavioral details for a destructive action.

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 covers both parameters with descriptions, and the tool description adds no extra semantic meaning. Parameter semantics are adequate but not enhanced beyond 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 'Delete messages in a Telegram chat' clearly states the action (delete), resource (messages), and scope (Telegram chat). It effectively distinguishes from sibling tools like send-message, edit-message, etc.

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 on when to use this tool over alternatives, such as when to delete single vs. multiple messages, or prerequisites like being an admin. No mention of when not to use it.

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?

Description discloses that it returns which IDs were deleted and which were not found, providing useful behavioral insight. Annotations indicate readOnlyHint=false (mutation) and description aligns, no contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: first states the action, second guides on usage and return value. 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?

For a simple one-parameter delete tool with no output schema, the description covers the purpose, input acquisition, and response behavior completely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. Description adds context about obtaining photo IDs via another tool, but the schema already describes the parameter 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 explicitly states the action 'delete' and the resource 'profile photos by their photo IDs', clearly distinguishing it from sibling tools like telegram-get-profile-photo and telegram-set-profile-photo.

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?

Provides clear guidance to use telegram-get-profile-photo to obtain the needed photo IDs. While it doesn't explicitly state when not to use it, the context is straightforward for a delete operation.

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

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

The annotations already mark the tool as destructive (destructiveHint: true). The description adds no further behavioral context beyond that, such as whether deletion is permanent, if it requires specific permissions, or if there are rate limits.

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 efficiently conveys the purpose. However, it could include brief usage notes without losing 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?

For a destructive tool with no output schema, the description lacks details on what happens after deletion (e.g., success response, error cases). It is adequate for a read operation but minimal for a write/mutation 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 coverage is 100%, so baseline is 3. The description does not add any additional meaning to the parameters beyond what the schema already provides (chatId and messageIds with their descriptions).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Delete scheduled messages in a Telegram chat', specifying the verb (Delete), resource (scheduled messages), and scope (Telegram chat). It distinguishes from siblings like 'telegram-delete-message' which deletes already sent messages, and 'telegram-send-scheduled'.

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 'telegram-delete-message', nor does it mention prerequisites (e.g., having scheduled messages) or conditions (e.g., cannot delete already deleted scheduled messages).

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

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

Annotations indicate destructiveHint=true and readOnlyHint=false, but the description adds critical behavioral details: 'irreversible' and 'requires confirm:true'. These go beyond annotations, informing the agent of permanent consequences and the mandatory confirmation parameter, which the schema also requires.

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 extremely concise: two sentences that front-load the core action and immediately follow with the critical irreversible+confirm context. Every sentence earns its place with no redundant or verbose phrasing.

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 low complexity (3 simple params, no output schema, clear annotations), the description covers all key aspects: what it does (delete own stories), behavioral notes (irreversible), and a required confirm flag. It is complete enough for an agent to understand and invoke 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 coverage is 100% with clear descriptions for all three parameters (ids, chatId, confirm). The description only echoes the confirm requirement without adding new semantic meaning. Baseline is 3 because schema already provides full parameter documentation.

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?

Description clearly states 'Delete one or more of your own stories' using a specific verb and resource, distinguishing it from siblings like telegram-delete-message (deletes messages) and telegram-send-story (sends stories). The phrase 'your own stories' clarifies ownership, leaving no 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 does not explicitly compare this tool to alternatives or provide when-to-use guidance. It implies usage for deleting own stories but lacks statements like 'use instead of telegram-delete-message for stories' or preconditions. The irreversibility warning is helpful but not comparative.

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

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

Annotations already provide destructiveHint=true and readOnlyHint=false. The description adds the detail that it deletes 'all its message history', confirming the destructive scope. This adds value beyond annotations, though it doesn't mention irreversibility or side effects like removing associated data.

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 with no wasted words. It immediately communicates the core functionality.

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 destructive nature, two parameters, and no output schema, the description covers the essential action and scope but lacks guidance on prerequisites, return values, or error conditions. It is adequate but not comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%—both parameters (chatId, topicId) have descriptions that explain their purpose. The tool description does not add any additional 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 clearly states the verb 'Delete' and the resource 'forum topic', and specifies 'all its message history' to clarify scope. This distinguishes it from siblings like telegram-delete-message (deletes individual messages) and telegram-edit-topic (edits topics).

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 does not provide any when-to-use guidance, prerequisites, or alternatives. It lacks explicit context such as requiring the chat to be a forum or the topic to exist, and does not mention when not to use this tool.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, indicating a safe read operation. The description adds 'download' which implies reading but also local file writing, which is consistent. However, it does not disclose potential side effects like overwriting files or required permissions, so it adds limited value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that front-loads the action. No unnecessary words, perfectly concise for a straightforward tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (3 simple params, no output schema, annotations provided), the description is minimally complete. However, it omits details like error handling for missing media, file type, or size limits, which could be important for agent usage.

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 all three parameters having clear descriptions (chatId, messageId, downloadPath). The tool description does not add additional meaning beyond these schema descriptions, hence the baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'download', resource 'media from a Telegram message', and outcome 'to a local file'. It distinguishes this tool from siblings like sending messages or searching, as it's the only tool focused on downloading 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 guidance on when to use this tool vs alternatives, such as when a message contains text vs media, or prerequisites like having access to the chat and message. It implicitly assumes the user knows when to download, but no explicit usage context is 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?

Annotations indicate readOnlyHint=false and openWorldHint=true, consistent with an edit operation. The description adds that it returns JSON with updated fields and requires a Business subscription, providing useful behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no superfluous words: first sentence states purpose and identification method, second covers return type and prerequisite. Optimally 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?

Covers purpose, link identification, return format, and a key prerequisite. Without an output schema, the return mention is helpful. Could mention parseMode enum details, but schema suffices.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear parameter descriptions in the schema. The description adds context for the slug (trailing segment after t.me/m/) and clarifies that title and message are 'new' values, enhancing understanding without repeating schema text.

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?

Clearly states the action (edit), resource (existing business chat link), and identifier (slug). Distinguishes from sibling tools like create-business-chat-link and delete-business-chat-link.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly mentions the requirement of a Telegram Business subscription. The sibling list provides context for when to use this tool versus creating or deleting links, but no explicit when-not or alternative guidance.

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

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

Annotations already declare readOnlyHint=false, so description adds little beyond privilege note. No extra behavioral details like idempotency or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded, no unnecessary words. Efficient and clear.

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?

No output schema, description lacks return value details. Could explain behavior for 'add' vs 'update' (e.g., how it decides which). Privilege context is helpful but incomplete for a modification 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 coverage is 100%, so baseline is 3. Description does not add additional meaning to parameters beyond what schema 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?

Clearly states 'Add or update a fact-check annotation' with verb and resource. Distinguishes from sibling tools like 'telegram-delete-fact-check' and 'telegram-get-fact-check'.

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?

Mentions privilege requirements and geographic limitation, providing clear context for when to use. Does not explicitly name alternative tools but siblings are self-evident.

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

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

Annotations already indicate readOnlyHint=false and openWorldHint=true, so the description mainly adds the partial-update behavior. No further side effects, permissions, or return info are disclosed, which is acceptable given annotation coverage.

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?

Single sentence with a clarifying fragment, perfectly concise and front-loaded with the key action. Every word adds 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?

Despite moderate complexity (14 parameters), the description gives minimal contextual information. No details about effects, errors, or behavior after editing. Without an output schema, more context is warranted.

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 only 43%, and the tool description adds no additional parameter-level meaning beyond 'only pass fields to change'. For a mutation with many parameters, more guidance would help.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Edit') and the resource ('existing Telegram chat folder'), and references how to obtain the ID ('from telegram-get-chat-folders'), distinguishing it from related tools like create, delete, and reorder.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to pass only fields to change and that omitted fields retain values, which guides usage. However, it does not state when not to use (e.g., creation) or explicitly compare 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?

Annotations indicate readOnlyHint=false and openWorldHint=true, which are consistent with a mutation tool. The description does not contradict these. However, it adds minimal behavioral context beyond what annotations and schema provide, such as potential permission requirements or side effects. The description is adequate but not rich.

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 sentence that efficiently conveys the tool's purpose. It is front-loaded and contains no unnecessary 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?

With no output schema, the description does not explain return values or success/failure behavior. It covers the basic purpose but lacks completeness for a mutation tool that might have side effects or require permissions. It is minimally adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with each parameter having a description. The tool description lists the editable items (title, description, photo) which map to the parameters, but adds no additional meaning or constraints beyond the schema. 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 clearly states the action ('Edit') and the resource ('a group'), specifying the editable attributes (title, description, or photo). This distinguishes it from sibling tools such as telegram-create-group and telegram-edit-message.

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 does not provide guidance on when to use this tool versus alternatives like telegram-edit-message or telegram-edit-topic. It mentions 'supergroups only' for description in the schema, but this is a constraint, not comparative guidance. No explicit when-to-use or when-not-to-use information is present.

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

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

Annotations indicate readOnlyHint=false, meaning the tool mutates data. The description does not add any behavioral details beyond the mutation implication, such as whether the edit is immediate, any restrictions on editability, or side effects.

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 sentence that immediately conveys the tool's purpose with no unnecessary words. It is optimally concise and 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?

No output schema exists, but the description does not explain what the tool returns (e.g., the edited message object). It also lacks information about limitations (e.g., time limits on editing, cannot edit other users' messages). For a mutation tool with zero output schema, more context is needed.

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% (all parameters have descriptions). The tool description does not add any extra meaning beyond the schema; it simply restates the verb. Baseline score of 3 is appropriate when schema fully documents parameters.

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 explicitly states the action 'Edit' and the resource 'previously sent message in Telegram', making it clear what the tool does. It distinguishes from sibling tools like send-message (sending new) and delete-message (deleting), as editing is a distinct operation.

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 on when to use this tool versus alternatives such as telegram-delete-message or telegram-send-message. There is no mention of prerequisites, limitations, or context-specific usage.

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

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

The description adds minimal behavioral context beyond annotations. Annotations already indicate a write operation (readOnlyHint=false) with external side effects (openWorldHint=true). The description does not disclose potential side effects (e.g., notifications, permanent changes, media constraints) that would aid the agent.

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 sentence listing three actions, front-loaded with the core purpose. It is concise, readable, and avoids unnecessary words. The parenthetical clarifies caption clearing behavior efficiently.

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 (9 parameters, no output schema, annotations present), the description covers high-level capabilities but lacks details on conditional requirements (e.g., allowUserIds needed when privacy='selected') and parameter interactions. It is adequate for basic understanding but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. The description adds value by grouping operations: 'replace media' (implicitly references filePath and type), 'update caption ('' clears it)' (explicitly explains special behavior), 'change privacy rules' (references privacy). This contextual grouping helps the agent understand parameter interactions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Edit'), the resource ('an existing story'), and specific operations ('replace media, update caption, or change privacy rules'). It distinguishes from siblings like telegram-send-story (create) and telegram-delete-stories (delete).

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 does not explicitly state when to use this tool vs alternatives (e.g., telegram-send-story for new stories, telegram-delete-stories for removal). It lacks prerequisites or exclusion criteria, though the tool's purpose is self-evident.

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

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

Annotations indicate readOnlyHint=false (write operation) and openWorldHint=true (potential side effects). The description mentions editable fields but does not disclose behavioral details like required permissions, rate limits, or impact on topic history. It adds minimal behavioral context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the verb and resource, then lists all possible modifications. Every word is purposeful, no fluff. It is appropriately sized for the tool's complexity.

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 6 parameters (2 required), no output schema, and openWorldHint, the description adequately lists the editable fields but omits contextual details like required permissions (e.g., must be admin), possible errors, or return behavior. It provides minimum viable completeness but leaves gaps for safe operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with each parameter having a description. The tool description mildly augments by listing high-level actions (rename, change icon, etc.), but does not add syntax or format details beyond what the schema provides. Baseline 3 is appropriate since the schema 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 clearly states the verb 'Edit' and resource 'forum topic', and enumerates specific actions: rename, change icon emoji, open/close, show/hide. It effectively distinguishes from sibling tools like 'create-topic' and 'delete-topic' by specifying the edit operation.

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 (e.g., edit-message, toggle-forum-mode). It does not mention prerequisites such as admin permissions or that the chat must be a forum supergroup. Without explicit usage conditions, the agent may misuse the tool.

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

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

Annotations (readOnlyHint, openWorldHint) already convey read-only nature; description adds that it returns a URL for a public story, consistent with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence with no filler, efficiently communicates the tool's purpose.

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 low complexity (2 params, no output schema) and good annotations, the description is complete and sufficient for agent understanding.

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 provides 100% coverage with descriptions; description adds important context that the story must be 'public', which is not in 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 uses a specific verb 'Get' and clearly identifies the resource as a 'shareable t.me/… URL for a public story', distinguishing it from sibling tools like telegram-get-story-views.

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 explicit when-to-use or when-not-to-use guidance is provided; the description only states the tool's function without discussing alternatives or prerequisites.

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

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

The description only states the basic function. It does not disclose behavioral traits such as whether the original message is preserved, if sender info is kept, or permission requirements. Annotations are minimal (readOnlyHint=false, openWorldHint=true) and description does not add context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no wasted words. Efficiently conveys the core functionality.

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 complexity of message forwarding (e.g., how forwarding works in Telegram, whether it's a copy or move, limitations), the description is insufficient. No output schema exists to explain return values. The description lacks essential behavioral details.

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 three parameters (fromChatId, toChatId, messageIds). The description adds no additional meaning beyond a general statement of purpose. 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 'Forward messages between Telegram chats' clearly states the action (forward) and the resource (messages between chats), distinguishing it from siblings like send-message or edit-message.

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 on when to use this tool versus alternatives like send-message or when not to use it (e.g., limitations on forwarding to specific chat types). No exclusion criteria or context 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?

Annotations indicate readOnlyHint and openWorldHint. The description adds beyond by specifying the kinds of events included (bans, edits, pins, role changes). It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: first states the purpose with verb and resource, second provides examples. No fluff, appropriately sized.

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 description covers the core functionality and examples of returned data. However, with no output schema, a brief mention of return format (e.g., list of events with timestamps) would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all three parameters. The description does not add additional meaning to the parameters beyond the schema, so it meets the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves the admin action log (recent event history) of a supergroup or channel, and lists specific event types (bans, edits, pins, role changes). This distinguishes it from sibling tools like telegram-get-chat-info or telegram-get-chat-members.

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 explicit guidance on when to use this tool versus alternatives. The name and description imply it's for auditing admin events, but it doesn't mention when not to use or compare to other log 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?

Annotations indicate readOnlyHint and openWorldHint as true, and the description adds that non-raw media data is returned. It also details pagination behavior and the hidden parameter, which goes beyond annotations without contradicting them.

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 paragraph that efficiently covers purpose, pagination, hidden option, and output summary. Every sentence adds value and it is appropriately 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?

Despite no output schema, the description specifies the returned metadata fields (id, date, expireDate, caption, mediaType, counters), which is sufficient for an agent to understand the tool's output. It covers the essential aspects needed for correct usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with parameter descriptions. The description adds valuable context for 'next' and 'state' (e.g., 'pass the returned state back') and explains the effect of 'hidden', enhancing 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 clearly states the action: 'Fetch active stories from contacts/channels the user follows.' This is a specific verb-resource pair that distinguishes it from sibling tools like telegram-get-peer-stories (stories for specific peers) and telegram-get-stories-by-id (by ID).

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 explains pagination using 'next' and 'state', and when to use 'hidden:true' for muted/archived peers. It provides clear guidance on how to use the tool but does not explicitly cover when not to use it or contrast with alternatives, though the context is adequate.

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?

Beyond annotations (readOnlyHint, openWorldHint), the description adds details: 'Read-only', field structure with optional fields (e.g., userId undefined for anonymous), and pagination. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (~80 words) and front-loads the main action. It could be more structured (e.g., bullet points) but remains efficient and readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description enumerates returned fields, permissions, pagination, and filter. It covers prerequisites, options, and read-only nature, making it fully informative for an 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?

The input schema has 100% coverage with clear descriptions. The description reinforces pagination and gift filter but adds minimal new semantic meaning 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 clearly states the tool lists boosts applied to a channel/supergroup, with specific verbs and resource. It provides field details but does not explicitly differentiate from the sibling tool 'telegram-get-boosts-status', which likely returns boost status.

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 mentions requiring channel admin permissions and supports pagination and gift filtering, indicating when to use it. However, it does not explicitly state when not to use it or provide alternatives like 'telegram-get-boosts-status'.

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

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

Annotations already mark as read-only and open-world; description adds detailed behavioral context (what fields are returned, underlying API method). Does not contradict annotations. No mention of rate limits or side effects, but appropriate for a read-only 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?

Very concise: front-loaded with purpose, then enumerates return fields in two sentences. No redundancy. Every sentence adds 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?

For a simple read-only query tool with one parameter and comprehensive schema, the description fully explains what the tool does, what it returns, and its read-only nature. No gaps given available structured fields.

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 provides 100% description coverage for the single 'chat' parameter, explaining accepted formats. Description does not add additional parameter meaning 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?

Clearly states it fetches boost status of a channel/supergroup and lists returned fields. Distinguishes from siblings by specifically mentioning 'premium.GetBoostsStatus' and returns specific boost metrics, unlike get-my-boosts or get-boosts-list.

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?

Implies use for checking boost stats of a chat, but does not explicitly explain when to choose this over related tools like get-my-boosts (which retrieves user's own boosts) or get-boosts-list (lists boosters). No exclusion criteria 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?

Annotations already indicate readOnlyHint=true and openWorldHint=true, which the description does not contradict. The description adds behavioral context about required permissions (admin rights, Premium). It does not fully describe failure cases or data freshness, but it is transparent about key requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no fluff. The first sentence states the core function and data, the second provides constraints and alternatives. Every word 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?

Given no output schema, the description lists the types of data returned (followers, views, etc.), which is helpful. It hints at includeGraphs for raw data. It could be more complete by describing the output structure, but it is adequate for a stats tool with sibling differentiation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with decent parameter descriptions. The description adds context about includeGraphs returning raw graph data and chatId being for broadcast channels, but this is marginal beyond the schema. 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 clearly states it gets broadcast channel statistics and lists specific metrics (followers, views, shares, reactions). It distinguishes itself from the sibling tool 'telegram-get-megagroup-stats' for supergroups, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says when to use (broadcast channels only) and when not to (supergroups should use telegram-get-megagroup-stats). It also notes admin rights and potential Premium requirement, providing clear usage 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?

Annotations indicate readOnlyHint and openWorldHint. The description adds valuable context: the requirement for Telegram Business, the empty list behavior, and the fields in each entry, which goes beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no wasted words. The first sentence front-loads the purpose, and the second provides necessary details.

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 simple list tool with no input schema and no output schema, the description fully explains what the tool returns (including specific fields), the requirement, and behavior when empty. No 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 tool has no parameters, and schema coverage is 100%. Baseline for 0 parameters is 4, and the description does not need to add parameter info.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists Telegram Business chat links, details the contents of each entry (t.me/... link, prefilled message, title, views, entityCount), and distinguishes from siblings like create/edit/delete/resolve.

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 specifies the prerequisite (Requires Telegram Business) and the empty list behavior when none configured, providing clear guidance on when to use this tool. However, it does not explicitly contrast with sibling tools for creating or editing.

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

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

Annotations declare readOnlyHint=true and openWorldHint=true. The description adds behavioral details beyond annotations, such as what happens on large gaps (returns a dialog snapshot) and the stateless nature of the cursor. It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but each sentence serves a purpose. It front-loads the main action, then explains cursor distinction, gap handling, and statelessness. Some redundancy exists (e.g., 'per-channel' repeated), but it remains efficient. A 5 would require even tighter wording, but it's 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?

Given no output schema, the description adequately describes return values: 'compact newMessages[], otherUpdates[], and new {pts, isFinal, timeout?}'. It also covers edge cases (large gap), and since schema coverage is 100%, all parameter meanings are clear. It is complete enough for an agent to use 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 coverage is 100%, so baseline 3. The description adds minimal extra meaning beyond the schema: it confirms 'chatId' is channel/supergroup ID or username, 'pts' is per-channel, 'limit' has default 100, 'force' is rarely needed. Overall, the schema already explains parameters well, so description adds marginal value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Fetch new messages and updates for a single channel/supergroup since a known per-channel pts cursor.' It uses a specific verb ('Fetch'), specifies the resource ('new messages and updates'), and distinguishes itself from the sibling 'telegram-get-updates' which uses a global cursor.

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 explicitly contrasts this tool with 'telegram-get-updates' (global cursor vs. per-channel). It also instructs on handling large gaps: 'hints to resync via telegram-read-messages.' Additionally, it notes the stateless cursor and that the agent stores pts, providing clear usage guidelines.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds that the tool returns names and chat counts, providing more specific return value context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, clear, and concise sentence with no extraneous information—every word adds 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?

For a simple list retrieval with no parameters and no output schema, the description adequately specifies what is returned (names and chat counts). Some details like pagination or limits could improve completeness, but the current level is sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters (0 params, 100% schema coverage), so the description does not need to add parameter information; baseline is 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves a list of Telegram chat folders (filters) including their names and chat counts, distinguishing it from sibling tools that create, delete, edit, or reorder folders.

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 explicit guidance on when to use this tool versus alternatives like get-suggested-folders or other folder manipulation tools; usage is implied by the tool name and 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?

Annotations already indicate readOnlyHint=true, so the description aligning with 'Get' is consistent but adds no new behavioral context. It does not disclose potential errors, rate limits, or authentication requirements.

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?

Single sentence, directly states the tool's purpose and key information returned. No extraneous words, clearly 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 simple read tool with one param and annotations providing safety info, the description covers the main outputs. However, without an output schema, listing a few fields is helpful but leaves uncertainty about the full response structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single parameter chatId, with a clear description ('Chat ID or username'). The tool description does not add additional meaning or format details 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 clearly identifies the action ('Get') and the resource ('detailed info about a Telegram chat'), and lists specific fields (name, type, members, description, forum status), which distinguishes it from sibling tools like get-chat-members or get-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?

No explicit guidance is provided on when to use this tool versus alternatives. The description implies it is for general chat info, but it does not mention when not to use it or reference other tools for more specific data (e.g., get-chat-members for member details).

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

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

Annotations (readOnlyHint, openWorldHint) indicate safety and possible incompleteness. The description adds no behavioral context beyond annotations, missing details like rate limits, pagination, or performance for large groups.

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?

Single sentence, concise and to the point. No unnecessary information, though a bit terse.

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 read tool with no output schema, the description is minimal. Missing details on return structure, pagination, and any side effects. Annotations partially compensate but leave 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 covers 100% of parameters with clear descriptions. The tool description adds no extra meaning beyond what's already in the schema, so baseline score 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?

Describes the tool as getting members of a Telegram group or channel, clearly specifying the verb and resource. Among siblings, it is distinct from other get-tools like get-chat-info. However, it lacks detail on scope (e.g., all members? paginated?).

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 on when to use this tool versus alternatives (e.g., get-chat-info for member count). No explicit when-not-to-use or context prerequisites.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds that it shows message previews, but doesn't contradict annotations. It provides minor extra context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences front-load the purpose and function. No wasted words, perfectly sized for the complexity.

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 simple single-parameter read tool with good annotations and schema coverage, the description is adequate. It explains what is returned (messages from non-contacts with preview). Lacks details on pagination or empty results, but sufficient.

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 has 100% coverage for the 'limit' parameter with a description. The tool description does not add any additional parameter-specific information, so 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 clearly states the tool retrieves incoming messages from non-contacts (contact requests) and previews them. It uses specific verb 'get' and resource 'contact requests', distinguishing it from sibling tools like telegram-get-updates.

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?

While no explicit when-to-use or when-not-to-use is stated, the purpose is specific enough that an agent can infer this is for viewing messages from non-contacts. No alternatives are named, but the context is clear.

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

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

Annotations already indicate readOnlyHint and openWorldHint. The description adds that the output includes phone numbers, but does not disclose other behaviors like pagination, data format, or authentication requirements.

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 sentence with no filler words. It is concise and front-loaded with the essential information.

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 is simple with one optional parameter and no output schema. The description states the core purpose but lacks details about the output structure, prerequisites, or full behavior, leaving some 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% for the single parameter. The description does not add any additional meaning beyond what the schema already provides, so baseline score 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 clearly states the action (Get), the resource (Telegram contacts list), and includes a specific detail (with phone numbers). It distinguishes this tool from siblings as the only one for retrieving contacts.

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 usage guidelines are provided. The description does not indicate when to use this tool over alternatives (e.g., telegram-get-profile) or what prerequisites exist (e.g., must be logged in).

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

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

Annotations declare readOnlyHint=true and openWorldHint=true, and description does not contradict. Adds value by listing return fields (discussionGroupId, discussionMsgId, etc.) and hints at non-destructive workflow. No additional behavioral gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences. First sentence efficiently lists returned fields. Second sentence adds actionable usage guidance. No unnecessary words; front-loaded with essential information.

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 no output schema, the description compensates by listing all return fields. Also explains the workflow and connection to other tools. Parameter documentation is complete. Sufficient for an agent to use 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 descriptions already clearly define chatId and messageId with 100% coverage. Description reinforces the purpose of parameters but does not add new semantic meaning beyond the schema. 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 clearly states the tool returns discussion group info for a channel post with comments enabled, listing specific fields. It distinguishes from siblings by specifying the return data structure and linking to telegram-send-message for workflow.

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?

Provides explicit usage context: for channel posts with comments enabled. Includes a use case example (using returned IDs with telegram-send-message). Does not explicitly mention when not to use, but gives sufficient guidance.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds 'across chats' scope detail but does not contradict annotations. Behavioral traits are covered but not significantly expanded.

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?

Single, clear sentence with no extraneous words. Every word 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?

Tool is simple with no parameters and no output schema. Description provides purpose and scope adequately. No additional details like pagination or format are necessary for this straightforward retrieval.

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?

No parameters exist; schema coverage is 100%. With 0 parameters, baseline is 4. Description adds no parameter info, which is appropriate since there are none.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves all saved message drafts across chats, using a specific verb ('Get') and resource ('saved message drafts'). It distinguishes from siblings like telegram-save-draft and telegram-clear-drafts.

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 (when you need to retrieve drafts) but does not explicitly state when to use it or provide alternatives or conditions. No guidance on when not to use.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds behavioral context: fact-checks are from independent fact-checkers in supported countries, and typical results may be empty. This enriches transparency beyond annotations without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no wasted words. The first sentence states the purpose, the second provides context on source and typical results, all essential information.

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?

While the description sets expectations for empty results and source, it lacks details on the output format or structure. With no output schema, the description could usefully describe what a fact-check annotation contains (e.g., text, link, rating). This gap lowers completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with both parameters (chatId, messageIds) fully described in the schema. The description adds no additional semantic detail about parameters, remaining at the baseline for high 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 states the tool retrieves fact-check annotations on channel messages, specifying the resource (fact-check annotations) and action (get). It distinguishes from sibling tools like telegram-delete-fact-check and telegram-edit-fact-check by focusing on reading.

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 when fact-checks are needed but does not explicitly state when to use alternatives or provide exclusion criteria. It sets expectations by noting most messages lack fact-checks but offers no direct comparison to other 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?

The description adds specific details about what settings are retrieved (auto-archived/muted, keep unmuted, hide read receipts, non-contacts need Premium) beyond the annotations (readOnlyHint, openWorldHint). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence that efficiently conveys all necessary information without redundancy or 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?

For a tool with no parameters and no output schema, the description sufficiently explains what the tool returns by listing the four specific privacy settings. No 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?

No parameters exist, so schema coverage is 100%. The description does not need to add parameter info; it is acceptable at baseline 4 for zero-parameter tools.

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?

Description clearly states 'Get your account-level global privacy settings' with a specific verb and resource, and lists the exact settings retrieved. This distinguishes it from sibling tools like the setter.

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 when one wants to check current privacy settings, but does not explicitly state when to use this tool versus alternatives like telegram-set-global-privacy-settings. No explicit guidance on exclusions.

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

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

Annotations already provide readOnlyHint and openWorldHint. The description adds behavioral context by specifying that the tool is a helper for setting up comment threads, implying it lists available groups. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no wasted words. First sentence states function, second adds context. Perfectly concise and 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?

Given the tool's simplicity (no params, no output schema, clear annotations), the description is adequate. It covers purpose and target user, though it could briefly note what the returned data looks like.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no parameters (0 params), so baseline is 4. The description correctly doesn't mention parameters, as there are none.

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 a specific verb ('List') and identifies the exact resource ('groups that can be linked as a discussion group to a channel you admin'). It distinguishes from sibling tools like telegram-get-chat-info by focusing on discussion group candidates for channel admins.

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 clearly states the target user ('channel admins') and the use case ('setting up comment threads'). While it doesn't explicitly exclude alternatives, the context is sufficient to guide appropriate use.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true. Description adds that it returns pack names and short names, which is helpful, but does not disclose any additional behavioral traits (e.g., whether archived sets are included, auth requirements, or data freshness).

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?

Description is concise with two short sentences: first states action, second states return value and purpose. No unnecessary words, front-loaded with key information.

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 simple list tool with no output schema and no parameters, the description adequately states what it returns (pack names and short names) and the intended follow-up use. Could mention if there are any limitations (e.g., pagination) but overall complete for its complexity.

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?

Tool has zero parameters and schema coverage is 100%, so description does not need to provide parameter details. Per guidelines, baseline 4 for zero-param tools.

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?

Description clearly states it lists all sticker sets installed by the user, with specific verbs and resource. Among sibling tools, it is distinct as a list-all-installed tool, not to be confused with get-sticker-set (specific set) or get-recent-stickers.

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?

Description implies usage by stating 'for use with other sticker tools', but does not explicitly say when to use vs alternatives like get-sticker-set or search-sticker-sets. No when-not-to-use guidance 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?

Annotations already mark it as read-only and open-world. Description adds context about default vs admin-specific queries, enhancing behavioral understanding without contradicting annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no waste. First sentence delivers purpose, second adds key usage detail. Efficient and 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?

Covers core usage with default vs admin query. No output schema but not critical for a simple list tool. Could mention pagination limit behavior but adequate.

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 has 100% coverage with descriptions. Description adds nuance about adminId default behavior, but does not significantly expand beyond schema. Baseline at 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?

Description clearly states 'Get list of invite links for a group or channel', specifying the verb, resource, and scope. It distinguishes from siblings like create-invite-link by focusing on retrieval.

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?

Provides clear guidance on default behavior (current account links) and how to query other admins via adminId. Lacks explicit when-not-to-use or alternatives, but purpose is well-defined.

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

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

Annotations (readOnlyHint, openWorldHint) already indicate safe read with dynamic schema. Beyond that, description adds admin rights requirement and specific rate limiting details, which are critical for agent planning and not covered by annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences pack essential details: data contents, sibling differentiation + prerequisite, and rate limit warning. No extraneous text, information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, description covers return value types (members, messages, viewers, etc.) and explains the effect of includeGraphs. Together with annotations and guidance, the agent has sufficient context to use 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 coverage is 100% with adequate descriptions for all 3 parameters. The description does not add much more about parameters themselves but provides context about the return data (current vs previous period, top lists). Baseline 3 is appropriate as schema carries the load.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.