telemost-mcp-server

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

Annotations already provide readOnlyHint and safe behavior. The description adds the output format ('JSON envelope {ok, data, meta}'), 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: the first states the purpose, the second gives the output format. No wasted words; 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 has no parameters, annotations for safety, and an output schema, the description is complete. It clearly states what the tool does and the envelope of the response.

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?

With zero parameters, the baseline is 4. The description adds no param info, but none is needed as schema coverage is 100%.

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 ('returns') and the resource ('available ad networks and their minimum deposits'), and it distinguishes itself from sibling tools by focusing specifically on advertising data.

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 compare ad networks and their deposits), and while it doesn't explicitly mention when not to use it, the context of sibling tools makes the usage 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?

Beyond annotations (readOnly, idempotent), description adds key behavioral info: returns JSON envelope, warns that response data is untrusted third-party text. This helps agent handle responses safely.

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

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

Four sentences, each adding value: purpose, time window, return format, security warning. Front-loaded with verb and resource. 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?

Given annotations (readOnly, idempotent) and output schema, description covers essential context: ad discovery, 14-day limit, return envelope, and untrusted data warning. Complete for this tool's 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?

Schema describes period with detail but query has no description. Description adds global context but does not explicitly define query semantics. With 50% schema coverage, description partially compensates.

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 what the tool does: 'Telegram ad intelligence and competitor analysis: discover ad posts running on channels, what and where competitors advertised, with creatives.' Differentiates from sibling tools like telemost_posts_search which are for regular posts.

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 usage for ad intelligence and competitor analysis, and mentions searches last 14 days. Does not explicitly exclude alternatives or provide when-not-to-use, 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 declare readOnlyHint, idempotentHint, and destructiveHint, making the safety profile clear. Description adds context that the tool returns a machine-readable catalog with prices and schemas, enhancing transparency about output content.

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 convey the tool's purpose and key details. The first sentence front-loads the core function, and the second adds the optional filter and payment status without superfluous 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 read-only catalog tool with no output schema, the description sufficiently explains what the tool provides (prices, schemas, examples) and that it is free. It does not describe response format, but given its simple purpose, the description 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 coverage is 0%, but the description enumerates the valid values for the 'block' parameter (data|statistics|ads|reference), which matches the schema enum. However, it does not explain what each block represents, leaving some ambiguity.

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 is a catalog of all paid Telemost tools, listing prices, schemas, and examples. It distinguishes itself from sibling tools which are individual functional tools (e.g., telemost_ads_networks, telemost_stats_channel).

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 mentions 'Free' and 'No payment required', implying use for discovery before using paid tools. However, it does not explicitly state when not to use or mention alternative tools for specific actions.

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

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

Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds critical safety context: third-party text is returned verbatim and should be treated as untrusted data. It also outlines the JSON envelope structure, going 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 two sentences plus a brief note on return structure and safety. It is front-loaded with purpose and use cases, with no redundant or extraneous text.

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 (2 parameters, 1 required), the description covers purpose, use cases, return format, and safety considerations. With an output schema implied, the mention of the JSON envelope 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?

Schema description coverage is 50%, with only 'region' having a description. The description does not elaborate on the 'channel' parameter format or the precise effect of 'region', beyond noting it is a routing hint. It provides adequate overall context but does not fully compensate for the missing parameter details.

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 verbs like 'Vet', 'enrich', and 'look up' with a clear resource ('channel data'). It distinguishes this tool from sibling tools (e.g., telemost_stats_channel) by emphasizing it provides both analytics and profile data in one call.

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 contexts for use: vetting a channel, enriching a dataset, or looking up channel data. It implies a general-purpose role compared to more specialized siblings, though it does not explicitly state when not to use it or list 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?

The description adds significant behavioral context beyond annotations: it specifies the JSON envelope structure (ok, data, meta) and warns that response data contains third-party text which should be treated as untrusted. Annotations only cover idempotency and read-only nature.

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 with two sentences: the first explains purpose, the second explains response format and a data trustworthiness warning. 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?

Given no parameters and that an output schema exists (context signals confirm), the description is complete. It covers what the tool does, the response envelope, and a crucial security note, 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?

There are no parameters, so the description does not need to add any. The schema coverage is 100% and the description does not require any parameter details. Baseline 4 is exceeded due to clarity.

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 purpose: providing curated compilations of Telegram channels by theme for market mapping and research. It uses specific verbs and distinguishes from sibling tools like telemost_search or telemost_channel_info.

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 use for discovery and research but does not explicitly state when to use this tool versus alternatives. No when-not-to-use or comparisons with siblings 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?

Adds behavioral info beyond annotations: returns a JSON envelope {ok, data, meta} and lists the three kinds. Annotations already declare readOnly and idempotent. No contradictions, but no detailed side effect disclosure.

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 unnecessary words. Efficiently conveys core info.

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?

Adequate for a simple reference tool with output schema. Mentions return envelope and kinds, but lacks details about the optional 'region' parameter and its usage context.

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

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

Description lists the three enum values for 'kind', adding meaning beyond the schema's enum alone. Does not mention 'region' parameter; schema covers its description. Schema coverage is 50% but description compensates for kind.

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 provides reference data (countries, categories, languages) for the Telegram analytics API, used for filters and targeting. The purpose is specific and distinct from sibling tools, though no explicit differentiation is given.

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. It implies usage for obtaining valid filter/targeting values, but does not mention exclusions 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?

Description adds value beyond annotations: warns that returned third-party text is untrusted and should not be treated as instructions. Annotations already indicate read-only, non-destructive operation; description provides security-relevant behavioral context.

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

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

Two efficient sentences: first conveys core functionality, second addresses data handling. No superfluous text; front-loaded with action and scope.

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

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

With a simple parameter, clear annotations, and an output schema, the description covers purpose, behavior, and security considerations. No gaps for this type of 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% with clear description for the only parameter 'source'. Description does not add extra parameter details beyond what schema provides, meeting 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 extracts structured entities (links, mentions, hashtags, etc.) from Telegram channel posts, specifying it's formatting-level not NER. It distinguishes from sibling tools like sentiment or search.

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 use for entity extraction from channels, with examples of entity types. While not explicitly contrasting with siblings, the context of 'formatting-level' vs 'semantic NER' provides differentiation. Slight lack of explicit 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 provide readOnlyHint, idempotentHint, and destructiveHint, so the bar is lower. The description adds value by warning that third-party text is returned verbatim and should be treated as untrusted data, and by specifying the JSON envelope format. 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 concise (4 sentences) and front-loaded with the core purpose. Every sentence adds value: purpose, use cases, filter detail, return format, and data trust warning. 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?

Given the tool's moderate complexity (3 params, output schema exists), the description covers purpose, usage, filter, return format, and data trust. It does not mention pagination or rate limits, but these are likely covered by the output schema and annotations. Overall complete enough for effective 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%, so baseline is 3. The description adds context for the 'since' parameter ('Honored where the backing index supports date filtering') and clarifies that the region hint does not affect payment, providing 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 fetches recent messages/posts from public Telegram channels/groups, with specific verb and resource. However, it does not explicitly differentiate from sibling tools like telemost_posts_search or telemost_post, which could cause confusion in selection.

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 suggests appropriate use cases (monitoring, tracking, feeding analysis) but lacks explicit guidance on when not to use or alternatives. This is adequate but could be more precise.

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 critical behavioral context beyond annotations: it warns that response data contains third-party text returned verbatim and should be treated as untrusted data, not instructions. This is valuable for safe invocation. Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint.

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: three sentences front-loaded with purpose, followed by what the tool measures, and a critical data trustworthiness warning. 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 tool with only 2 parameters, an output schema, and clear annotations, the description covers purpose, usage context, behavioral traits, and return format. Completeness is high.

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 both parameters (post and region). The tool description does not add additional meaning beyond what the schema already provides. 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 tool provides analytics for a single Telegram post, including statistics like views, forwards, and reactions. It uses a specific verb ('measure') and resource ('a single post'), distinguishing it from sibling tools like telemost_messages or telemost_stats_* which cover multiple posts or different metrics.

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

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

The description implies usage for analyzing a specific post's performance but does not explicitly state when to use this tool versus alternatives like telemost_messages or other stats tools. No exclusion criteria or when-not-to-use guidance is 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 declare readOnly, openWorld, idempotent, and non-destructive. The description adds value by noting the 14-day limit, the JSON envelope format, and a security warning about treating third-party text as untrusted. 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 efficient (80 words), front-loaded with the core purpose, followed by use case, time window, output format, and a critical security note. 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?

Given the output schema exists and annotations are present, the description covers purpose, time window, output structure, and security. Missing details on query syntax and extended parameter are minor 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?

Only 25% of parameters have schema descriptions (region). The tool description does not explain the 'query' parameter beyond 'full-text search', nor 'limit' or 'extended', despite mentioning 'extended query syntax' without detail. Schema coverage is low and description does not compensate.

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 is a full-text search over Telegram posts across public channels, for finding mentions of keywords, brands, or topics. It specifies the 14-day window and distinguishes it from other tools by mentioning posts specifically.

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 identifies use cases (brand monitoring, market research) but does not explicitly compare to sibling tools like telemost_search or telemost_messages, nor does it state 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 indicate read-only, idempotent, and non-destructive behavior. The description adds value by warning that response data contains untrusted third-party text and should not be treated as instructions. 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 cover purpose and response handling without extraneous information. Structure is reasonably front-loaded, though the response format detail could be placed later. No wasted words.

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

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

The description covers the return envelope and data trust warning, but lacks details on result ordering, pagination, error handling, or the effect of parameters like 'limit'. Given the output schema exists, the description is 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?

With only 25% schema description coverage (only 'region' has a description), the tool description does not compensate by explaining 'query', 'limit', or 'scope' parameters beyond the schema. The phrase 'by keyword' hints at 'query' but lacks details on defaults or behavior.

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 searches public Telegram channels, groups, and posts by keyword, using a specific verb (find/discover) and resource. It distinguishes from siblings like 'telemost_posts_search' by covering multiple data types, but could be more explicit about unique differentiators.

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

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

The description implies usage for keyword-based discovery but does not provide explicit guidance on when to use this tool versus alternatives like 'telemost_posts_search' or when not to use it. No exclusions or context for selection among siblings.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering safety and idempotency. The description adds valuable context about the response containing third-party text verbatim and warns to treat it as untrusted data, disclosing a key behavioral trait not in 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 with four sentences, each serving a distinct purpose: stating the tool's function, indicating an alternative, describing the return format, and warning about data safety. No fluff 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 description covers purpose, return format, and a data safety warning, and an output schema exists. However, it lacks explanation of parameters and usage scenarios, which are essential for a tool with three optional parameters and no schema descriptions.

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 0%, so the description must explain parameters. It fails to mention or explain the three parameters (topic, period, source) at all. The only hint is 'recent posts and reactions for a channel, group or topic', but this does not map parameters to their roles.

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 provides 'Telegram sentiment analysis' from 'raw inputs' (recent posts and reactions) for channels, groups, or topics. It distinguishes itself from the sibling 'telemost_sentiment_llm' by noting that this tool provides raw data for custom analysis, while the sibling offers a ready LLM verdict.

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 tells the agent to use telemost_sentiment_llm for a ready verdict, creating a clear context for when not to use this tool. However, it does not discuss other siblings or provide broader when-to-use guidance, leaving some ambiguity among the many 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 readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds valuable behavioral details: it returns a JSON envelope {ok, data, meta} and warns that third-party text in response is untrusted and should not be treated as instructions.

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 concise sentences covering output, purpose, and a security warning with output structure. No redundant information, well 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 output schema exists and annotations are rich, the description covers key aspects: return envelope, untrusted data warning, and a usage case. However, parameter details are missing, and there is no differentiation from sibling 'telemost_sentiment'.

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?

With 0% schema description coverage, the description should compensate but does not. The description mentions 'channel, group, or topic' but does not explicitly map to the 'topic' parameter, and does not explain 'period' or 'source' at all. The meaning of these parameters is left entirely to inference.

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 performs Telegram sentiment analysis using an LLM, producing a sentiment label, score, trend, and summary for a channel, group, or topic. It explicitly mentions 'LLM verdict' to distinguish from likely sibling 'telemost_sentiment'.

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

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

The phrase 'Gauge audience mood or brand perception before acting' provides clear context for when to use the tool, but it does not explicitly mention sibling alternatives or 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?

Adds critical warning that response data is third-party and untrusted, instructing not to treat as instructions. This goes beyond annotations (readOnlyHint, openWorldHint, idempotentHint) and is essential for safe usage.

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 purpose, second warns about response data. 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?

Given output schema exists and annotations are rich, description covers purpose, response envelope, and data trustworthiness. Missing parameter format hint, but overall adequate for a simple 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?

Input schema has one parameter 'channel' with 0% description coverage. Description mentions 'given one' but does not specify format (e.g., username, ID) or constraints. Single parameter reduces ambiguity, but lack of detail limits clarity.

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 finds similar Telegram channels by topic and audience for competitor analysis. Verb 'find' and resource 'similar channels' are specific. Distinct from sibling tools like telemost_channel_info or telemost_search.

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?

Describes context (competitor analysis, channel discovery) but does not explicitly exclude alternatives or provide when-not-to-use guidance. However, the purpose is clear enough for an agent to infer 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, openWorldHint, idempotentHint, and destructiveHint. Description adds value by warning that response contains third-party text and to treat it as untrusted data, which is beyond the annotations. Also describes the return envelope. 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?

Two sentences, highly efficient. First sentence lists metrics and states purpose, second sentence provides crucial data trust warning. No filler, front-loaded with the most important 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 the presence of an output schema (so return values explained) and annotations covering safety and idempotence, the description is fairly complete. It covers purpose, key metrics, data trust note. Could mention that the channel must be public, but that is implied by 'any public channel'. Reasonably thorough for a stats 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 50%, but description adds no details about the 'channel' parameter beyond the schema's simple string type. The 'region' parameter is explained in the schema with enum and a note that it doesn't affect payment, which is adequate. Description does not compensate for the missing 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 it provides 'Telegram channel analytics and statistics' with a specific list of metrics (subscribers, growth, average post views, etc.), distinguishing it from sibling tools that focus on individual metrics like telemost_stats_engagement or telemost_stats_reach. Positions itself as a quick health check, making its 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?

Implicitly suggests use for a broad overview of a channel's performance, and notes that metrics are only populated if the channel exposes them. However, no explicit guidance on when to use this vs. more specific sibling tools (e.g., telemost_stats_engagement) or when not to use it. A clear point of differentiation is hinted but not stated outright.

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 idempotentHint=true. The description adds the return envelope format ({ok, data, meta}) and explains the three metrics, which is non-trivial context but does not disclose other behavioral traits like data limits or calculation methodology.

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 the main purpose and key metrics. Every sentence adds value: first sentence defines what the tool does, second sentence describes the return format. 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?

The description explains the return envelope and lists the metrics, but does not provide context about the 'channel' parameter, data source, or how metrics are calculated. Given the output schema exists, the mention of {ok, data, meta} is helpful but still leaves gaps for a complete 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 description coverage is 50%: 'aggregation' has a description, but 'channel' does not. The tool description does not explain any parameters. For a tool with 50% coverage, the description should compensate by describing all parameters, but it does not.

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 provides engagement analytics (ER, ERR, ERR24) over time, benchmarking audience activity and channel performance. This distinguishes it from sibling tools like telemost_stats_reach or telemost_stats_subscribers.

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 versus alternatives like telemost_stats_channel or telemost_stats_mentions. The purpose is implied but no when-not or exclusion criteria 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?

Describes return format (JSON envelope with ok, data, meta) and warns that response data contains third-party text to treat as untrusted data. This adds significant behavioral context beyond annotations (readOnlyHint, idempotentHint, etc.). No contradiction found.

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?

Five sentences covering function, usage alternatives, history limit, output format, and data trust warning. Each sentence adds distinct value with no redundancy or filler.

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

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

Given the tool's moderate complexity (2 params, no nested objects, output schema exists), the description covers what it does, when to use, return structure, and safety guidance. No obvious gaps for an API with good annotations and schema.

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 adds value by explaining the 'all' period maps to max 365-day window and actual window is returned in meta.window. Minor extra context beyond schema, but more could be said about channel format.

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 tracks mentions and citations of a given Telegram channel across other channels, including share of voice. It distinguishes itself from keyword tracking tools, making the purpose specific and actionable.

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 advises when to use this tool vs. alternatives: 'For keyword or brand tracking across posts, use the word tracker or post search.' Also notes history window up to one year, providing clear context for selection.

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, openWorldHint, idempotentHint. Description adds return format details (JSON envelope with ok, data, meta) and clarifies it returns a chart over time, which is beyond annotation info. 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?

Two sentences, front-loaded with purpose, 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?

Tool is simple with rich annotations and output schema. Description covers purpose and return format. Minor omission: does not explain the meaning of 'ok' or data structure, but output schema exists.

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 50% (only 'aggregation' has description). The description does not explain the 'channel' parameter or add any meaning beyond schema. Fails to compensate for missing 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 the verb ('get analytics'), resource ('average post reach chart for a channel'), and output format ('JSON envelope'). It distinguishes from sibling stats tools by specifying reach analytics.

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 telemost_stats_channel or telemost_stats_engagement. The description does not mention when to use or 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, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds the return format ('JSON envelope {ok, data, meta}'), which is useful but not extensive. Additional details like authentication requirements or error behavior are missing but compensated 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?

The description is two sentences with no redundant information. It front-loads the core purpose and efficiently covers scope and return format. 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?

Given the presence of an output schema and three parameters (one required), the description sufficiently conveys the tool's operation. It explains the return structure and time granularity. However, it does not clarify what 'subscriber growth' means exactly or how the data is computed, but this is minor for a simple analytics 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 67%: 'region' and 'aggregation' have descriptions, but 'channel' lacks one. The description only reiterates aggregation values ('day/week/month/year'), adding minimal value beyond the schema. No additional semantics for 'channel' or 'region' are provided, leaving the required parameter undocumented.

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 purpose: 'subscriber growth chart for a channel, track audience growth or decline over time'. It uses specific verbs ('track'), identifies the resource ('subscriber growth for a channel'), and distinguishes from sibling stats tools like telemost_stats_engagement and telemost_stats_reach.

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

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

The description implies usage for subscriber growth tracking but lacks explicit when-to-use, when-not-to-use, or alternative guidance. However, given the sibling context, the purpose is distinctive enough to guide agent selection. A clear mention of when to prefer this over other stats tools would improve clarity.

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, idempotentHint, non-destructive), the description adds important behavioral traits: a 14-day search window, response envelope format {ok, data, meta}, and a critical security warning that third-party text is untrusted. This goes beyond what annotations convey, though rate limits and auth are not mentioned.

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 with no fluff. The first sentence front-loads the core purpose and modes. The third sentence adds an essential security note. It could be slightly improved by structuring mode options more explicitly, but overall it's concise and well-organized.

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 moderate parameter count (4), low schema coverage (25%), and presence of an output schema, the description covers the main use case, mode selection, time window, response format, and security. Missing: explanation of 'extended' parameter and when to choose by-period vs by-channels. But the output schema likely fills some gaps, so overall completeness 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 only 25% (only 'period' described). The description compensates by explaining mode options ('by-period' vs 'by-channels') and relating 'period' to a 14-day window. However, 'extended' parameter is not described, and 'word' lacks additional context beyond its name. Still, key parameters are adequately clarified.

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 tracks keyword/brand volume across public channels, with two modes (by-period, by-channels). It distinguishes from sibling stats tools like telemost_stats_channel (which likely tracks channel stats) and telemost_stats_engagement (which tracks engagement). The specific verb 'track' and resource 'keyword/brand volume' leave 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?

No explicit guidance on when to use this tool versus the many sibling tools. While the name and purpose imply it's for keyword tracking, an agent might confuse it with other stats tools that also track metrics. Implicit context from the description (keyword/brand tracking) provides some direction, but explicit when/when-not statements are absent.

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