Server Quality Checklist

Tool Scores

• telegram_channelA
  4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and openWorldHint=true, and the description aligns with this by using 'look up' with no mutation implied. The description adds useful behavioral context beyond annotations: only public channels are readable, private channels are not, and it returns exact subscriber counts plus activity cadence. It also implies the tool may surface stale/inactive channels, which is valuable warning behavior.

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

  Conciseness5/5

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

  The description is concise and front-loaded: the first sentence states the action and deliverables, and the second sentence gives practical use cases with a memorable example. Every sentence earns its place, and the stale-channel warning is compact yet highly informative.

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

  Completeness4/5

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

  Given there is no output schema, the description does a good job listing the expected output fields and the tool's key limitation (public channels only). It covers purpose, return contents, usage context, and a failure mode. It does not mention output shape or the extra API call cost for cadence, but those are covered by the schema and are not severe omissions.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the schema fully documents all three parameters, including the channel handle format, the format enum, and the cadence boolean. The description adds minor reinforcement by mentioning 'how often it posts' and 'public Telegram channel', but it does not add significant meaning beyond what the schema already provides.

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

  Purpose4/5

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

  The description clearly states a specific action ('Look up a public Telegram channel') and lists the exact fields returned: title, description, subscriber count, creation date, verification/scam flags, and posting frequency. It is clear and specific, but it does not explicitly differentiate this tool from its siblings, telegram_similar_channels or telegram_search_channels, so an agent must infer that this is for known handles rather than discovery or similarity.

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

  Usage Guidelines4/5

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

  The description gives explicit use cases: checking whether a channel is real, how large it is, and whether it is still active, including a concrete warning about dead channels with large subscriber counts. It provides clear context for when to use this tool, though it does not state when to prefer the sibling tools or explicitly exclude search/similarity scenarios.

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

• telegram_similar_channelsA
  4.2/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint and openWorldHint, so the safety profile is covered. The description adds useful behavioral context beyond annotations: results are based on shared audience rather than vocabulary, and result counts vary ('Large channels return roughly a dozen; small or very new ones return none'), which sets accurate expectations.

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

  Conciseness5/5

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

  The description is three focused sentences with no fluff. It front-loads the core action and differentiator, then adds a practical usage note and a caveat about result size. Every sentence earns its place.

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

  Completeness4/5

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

  For a tool with one required parameter, full schema coverage, and safety annotations, the description covers the essential conceptual model, typical use case, and result-size expectations. There is no output schema, but the format parameter in the input schema documents output shapes, so the missing return-structure detail is not a significant gap.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the baseline is 3. The description does not add new parameter-level guidance beyond the schema; the only relevant nuance is that 'a given channel' maps to the channel parameter, but this is already apparent from the schema and context.

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

  Purpose5/5

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

  Description uses a specific verb ('Return') and resource ('channels Telegram itself recommends alongside a given channel'), and clearly differentiates itself from keyword search by stating it is Telegram's 'own topical judgement, not a keyword match.' This makes the purpose unmistakable and distinct from its siblings.

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

  Usage Guidelines4/5

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

  The description gives explicit usage context: it is 'the way to discover channels whose names you do not already know' by starting from a known channel and walking outward. It also implies when not to use it (when you need keyword-based discovery), though it does not explicitly name sibling alternatives like telegram_search_channels.

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

• telegram_search_channelsA
  4.7/5.0
  Behavior4/5

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

  Annotations already establish read-only and open-world behavior. The description adds useful behavioral context: the search is Telegram's own, restricted to title and handle, and that short keywords are more effective—an important nuance for the agent's query strategy.

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

  Conciseness5/5

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

  Three sentences, all load-bearing: what it searches, when to use it versus the sibling, and a practical tip. No repetition of the title or schema, and the core distinction is front-loaded.

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

  Completeness5/5

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

  For a simple read-only search tool with fully documented parameters, this description provides enough to call it correctly: scope, matching criteria, use case, and sibling alternative. The format parameter already covers output shape, so no additional return-value explanation is needed.

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

  Parameters4/5

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

  Schema coverage is 100%, so the baseline is 3. The description goes beyond the schema by explaining that query semantics favor short topical words and that results are matched by title and handle, which meaningfully informs how the agent should set the query parameter.

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

  Purpose5/5

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

  The description clearly identifies the tool as Telegram's global search over public channels and groups, by title and handle. It explicitly distinguishes itself from telegram_similar_channels, which is the expansion step, so an agent can select the right starting point.

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

  Usage Guidelines5/5

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

  It states this tool is good for seeding a topic and names telegram_similar_channels as the alternative for expanding a seed into a neighbourhood. It also provides practical guidance that short topical words outperform sentences.

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