Server Quality Checklist

Tool Scores

• telegram_pollC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full transparency burden. It states the side effect ('Send') and lists return fields, which is helpful, but it omits important behavioral context such as authentication requirements, whether the chat_id actually overrides the default, rate limits, or failure behavior beyond an 'error?' field.

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

  Conciseness4/5

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

  The description is short and front-loaded with the main action. The return-shape line is useful and the whole thing is easy to parse. The markdown header adds negligible value but does not harm clarity.

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

  Completeness2/5

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

  For a side-effecting external messaging tool with no annotations and four parameters, the description is too thin. It lacks usage conditions, parameter details, and behavioral clarifications. The listed return dict partially covers output, but that does not compensate for the missing operational context.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description must compensate. It only adds context about a 'configured/default chat,' which loosely relates to chat_id, but it does not explain options, is_anonymous, required question format, or how chat_id interacts with the default. The return dict mentioning 'question' does not meaningfully document parameters.

  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 states the operation: 'Send a Telegram Poll' to a 'configured/default chat.' This is a specific verb+resource statement, and none of the sibling tools overlap with this action, so an agent can immediately identify what the tool does.

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

  Usage Guidelines2/5

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

  There is no guidance about when to use this tool versus alternatives, nor any mention of prerequisites or appropriate context. The phrase 'configured/default chat' hints at configuration but does not explain when an agent should invoke this tool.

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

• backtest_reportA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry the behavioral disclosure burden. It discloses the return dictionary including an 'error?' key, hinting at failure handling, but it does not state side effects, behavior on missing/invalid files, or assumptions about the JSON structure.

  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 a single front-loaded purpose line followed by a compact return-type listing. There is no filler, and every element adds useful information about what the tool does or returns.

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

  Completeness3/5

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

  The return dictionary provides a good map of outputs, but the two parameters remain effectively undocumented and error-handling detail is minimal. For a simple parser this is close to adequate, but explicitly defining 'top_n' and the expected location of 'file_path' would make it complete.

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

  Parameters2/5

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

  Schema description coverage is 0%, and the description never mentions 'file_path' or 'top_n'. 'top_n' can be inferred from 'top_trades_md', but the description does not compensate for the schema's silence regarding path format or the meaning/limits of 'top_n'.

  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 names a specific action and resource: 'Parse Freqtrade backtest-result JSON → markdown digest.' It also lists the exact return keys, making the tool's function concrete and clearly distinct from its unrelated siblings.

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

  Usage Guidelines3/5

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

  When to use the tool is implied by the input type ('Freqtrade backtest-result JSON'), but there is no explicit when/when-not guidance or mention of alternatives. Since all sibling tools are unrelated, there is no direct selection ambiguity, but the guidance is still implicit rather than stated.

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

• page_monitorA
  3.7/5.0
  Behavior4/5

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

  With no annotations, the description carries full responsibility for behavioral disclosure. It reveals state persistence location, return fields including is_first_check and error, and the notification action. It does not cover failure modes or rate limits, but the core behavior is transparent enough.

  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 extremely concise and front-loaded with the primary purpose. Each line adds value: state path, return format, and error field. No fluff or repetition exists.

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

  Completeness2/5

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

  Although an output schema exists (covering return values), the description lacks essential invocation context: the role of selector and the behavior when chat_id is defaulted. An agent cannot determine how to use the selector parameter or what happens without a chat_id, leaving the tool incompletely specified for correct use.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description must compensate for all parameter meaning. It only indirectly references the URL and Telegram notification (implying chat_id), but the selector parameter is entirely unexplained. This leaves a significant semantic gap for a required workflow.

  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 states a specific verb ('Check'), a clear resource ('URL'), and the full behavior (persist hash, notify on change). It clearly distinguishes this from sibling tools like telegram_poll or file_convert, as it is specifically a URL-change monitor.

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

  Usage Guidelines3/5

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

  The usage is implied through the description ('Check URL for changes; persist hash; notify Telegram on change'), but no explicit when-to-use or alternative guidance is given. It does not explain when to set chat_id or selector, which are needed for correct invocation in different scenarios.

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

• file_convertA
  3.8/5.0
  Behavior3/5

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

  The description discloses the return structure as a dict with status, output_path, output_format, preview, and optional error. It also lists all supported conversions. However, it does not mention whether the original file is modified, if output overwrites anything, or any permissions required. Since there are no annotations, the description carries the full burden, but it does provide core behavioral information.

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

  Conciseness4/5

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

  The description is compact and well-structured with a heading, a list of supported conversions, and a return type. It is front-loaded with the purpose, and every line earns its place, though it could elaborate on parameter meanings without bloating.

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

  Completeness3/5

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

  Given the low schema coverage and lack of annotations, the description provides the essential information: supported conversions and return format. However, it leaves ambiguity about parameter semantics and doesn't mention file system interactions or error conditions beyond the optional error key. It is mostly complete but has room for improvement.

  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?

  The input schema has no descriptions, so the description must compensate. The conversion matrix implies that 'path' is the source file and 'fmt' is the target format, but this is not explicitly stated. The allowed values for fmt are not enumerated directly, but can be inferred from the matrix. This is partial compensation, but not fully explicit.

  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 states the tool converts file formats and lists all supported conversion paths in a table. This is specific and distinguishes it from the unrelated sibling tools, so an agent knows exactly what this tool does.

  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 does not explicitly state when to use this tool versus an alternative, but given the sibling tools are unrelated, there's no confusion. The conversion matrix implicitly communicates the use case: if you need any of these conversions, use this tool. It doesn't mention when not to use, but that's acceptable given the scope.

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

• antimatter_scanA
  3.9/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral disclosure burden. It explains the two accepted source forms (file path or docker:container_name), that it scans and counts trades/errors/signals, and exactly what fields it returns, including an optional error field. It does not discuss permissions or max_errors behavior, but the read-only 'scan' framing plus detailed return contract gives a strong behavioral picture.

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

  Conciseness4/5

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

  The description is compact and front-loaded with the core purpose, followed by useful path syntax and return fields. The return-dict list is slightly redundant given that an output schema exists, but the overall structure is efficient and easy to scan.

  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?

  An agent can successfully invoke the tool based on this description: the required parameter format is clear, the optional parameter has a schema default, and the return contract is specified. The main gaps are undocumented max_errors semantics and lack of explicit sibling differentiation, but the core invocation path is well covered.

  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 0%, so the description must compensate. It does explain logs_path well, including the file-or-docker format with an example. However, max_errors is never mentioned, leaving its effect on recent_errors and counts to inference.

  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 states a specific verb and resource: 'Scan Freqtrade logs for trades / errors / signals.' It also lists the return contract, which makes its purpose unmistakable and distinguishes it from siblings like trade_signal or backtest_report even without naming them.

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

  Usage Guidelines3/5

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

  The intended use is implied by the description — it scans Freqtrade logs — but there is no explicit guidance on when to prefer this tool over alternatives, nor any exclusions or when-not-to-use conditions. The context is clear, but the tool is not positioned against its siblings.

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

• soc_lang_cardA
  3.9/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden of disclosing behavior. It does so meaningfully: selection is deterministic via a date hash, the same card is served all day, and the exact return dict keys are listed. Side effects and error behavior are not discussed, but the tool is inherently read-only and its core behavior is transparent.

  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 compact and front-loaded: a one-line purpose, followed by parameter constraints, deterministic behavior, and return shape. Every line adds useful information without repetition or filler.

  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 the tool's simplicity, two optional parameters, and an output schema, the description covers the essential invocation details: level options, focus choices, determinism, and return keys. Minor gaps such as timezone/date semantics or richer focus descriptions exist, but nothing blocks correct usage.

  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 description coverage is 0%, so the description compensates by documenting the allowed values for level (A1|A2) and listing all focus options as an optional context filter. It adds meaning the schema lacks, though it could further explain what each focus changes about the returned card.

  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 opens with a clear summary of what the tool does: it returns a daily language card pairing a German word at A1/A2 with a SOC term in EN/DE/RU. It names the resource and output precisely, though it does not explicitly differentiate it from the sibling word_of_day tool.

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

  Usage Guidelines3/5

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

  The description implies usage by explaining that selection is deterministic and that focus is an optional context filter with enumerated SOC domains. However, it does not explicitly say when to use this tool instead of alternatives like word_of_day, nor does it state exclusions or preferred contexts.

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

• trade_signalA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full behavioral burden. It does disclose the data source (Binance OHLCV), the algorithm, and the exact returned dict including an 'error?' field. It does not mention network dependency, rate limits, data recency, or behavior on invalid symbols/intervals, which are important for a live-data tool.

  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 tightly structured: one pipeline line, one symbol line, one interval line, and one return line. Every line adds a distinct piece of information, and the most important behavioral summary is front-loaded.

  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 simple two-parameter tool with an output schema, the description is nearly self-sufficient: it supplies symbol format, allowed intervals, and return shape. It omits edge-case behavior and the exact signal decision thresholds, but those are not required for a correct first invocation.

  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 description coverage is 0%, so the description must compensate. It does so by providing concrete symbol examples (BTCUSDT, ETHUSDT, SOLUSDT) and by constraining interval to '1h | 4h | 1d | 1w'—values absent from the schema. It doesn't explain every nuance of the parameters, but it gives an agent enough to invoke the tool correctly.

  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 opens with a precise pipeline: 'Binance OHLCV → RSI(14) + SMA20/SMA50 cross → BUY/SELL/HOLD'. It names the data source, the calculation, and the output category clearly, and the listed return fields confirm exactly what the tool produces. No sibling overlaps with this function, so no extra differentiation is needed.

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

  Usage Guidelines3/5

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

  Usage is implied rather than explicitly stated: the symbol examples and interval list suggest this tool is meant for generating trade signals from Binance OHLCV data. However, there are no when-to-use conditions, no mention of alternatives, and no exclusions such as 'not for backtesting or multi-symbol signals'.

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

• weather_alertA
  4/5.0
  Behavior4/5

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

  With no annotations available, the description carries full behavioral disclosure burden. It reveals the data source (Open-Meteo), no API key requirement, default cities, and returns a dict containing status, cities_checked, alerts, and errors. This is transparent for a simple read-only weather-checking operation, though it does not dive into failure modes beyond an errors field.

  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 compact, front-loaded, and uses a clear heading plus bullets. Every sentence adds useful information: what it does, default cities, authentication-free source, and return shape. There is no filler or redundant restating of the tool name.

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

  Completeness3/5

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

  The description covers the tool's core behavior, defaults, source, and return format, which is enough for a simple alert-checking tool. However, because there are no annotations and no schema descriptions, the description leaves some gaps: no explicit mapping of thresholds to parameters, no definition of temp change interval, and no handling explanation for invalid cities. It is adequate but not fully complete.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description must compensate, but it only generically mentions 'thresholds' and 'default cities'. It does not explain the specific parameters (cities, rain_threshold_mmh, wind_threshold_kmh, temp_change_threshold) beyond what the schema's names already convey. The return dict gives some indirect context, but substantial parameter guidance is missing.

  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 states a specific action ('Check weather for cities; return alerts when thresholds exceeded') and a clear resource. It also provides concrete details like default cities and the return structure, making the tool's purpose unmistakable even before opening the schema.

  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 clearly implies when to use this tool: to check weather and receive threshold-based alerts. It doesn't explicitly discuss alternatives, but none of the sibling tools serve the same purpose, so explicit exclusions are not necessary. The note about Open-Meteo and no API key gives helpful context for when this tool fits.

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

• word_of_dayA
  4.2/5.0
  Behavior4/5

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

  No annotations are present, so the description carries the full burden of behavioral disclosure. It discloses that selection is deterministic via 'hash of date+level' and that the same word is returned all day, which is a key behavioral trait. It also enumerates the returned fields, adding clarity beyond the bare tool name, though it does not discuss error semantics or timezone assumptions.

  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 compact and well structured, with purpose, parameter guidance, behavior, and return format each on their own line. Every sentence adds value, and there is no filler. The deterministic-selection note is especially useful and placed where it is easy to notice.

  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 simple single-parameter read-only tool, this description covers the essential selection criteria and output shape. It lacks a precise definition of what 'date' refers to and does not explain the possible values of the 'status' field, but these are minor gaps given the tool's simplicity and the presence of an output schema.

  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 description coverage is 0% and there are no enums, so the description must compensate. It does so by specifying 'level: A1 | A2', which defines the only parameter's allowed values. It does not elaborate on what happens with invalid values or whether 'A1' and 'A2' are case-sensitive, but the core semantic is present.

  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's resource: 'German word of the day with translations + IPA + examples' and explicitly states the return shape. Although it lacks an imperative verb like 'get', saying 'Returns dict' describes the operation precisely. It is also easily distinguishable from all sibling tools, none of which are word-of-day retrievers.

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

  Usage Guidelines3/5

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

  The description implies the use case: call when you need a German word of the day for A1 or A2. However, it does not explicitly state when to prefer this tool over alternatives or provide exclusions. There are no directly competing siblings, so the omission is not severely harmful, but explicit guidance is still absent.

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

• mcp_statsA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the full behavioral disclosure burden. It explicitly describes the return dict structure, notes that data is also persisted to a stats JSON file for cross-process visibility, and frames the operation as a snapshot, implying read-only inspection. This is strong context, though it does not discuss any failures or reset 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 compact: a front-loaded purpose line, a terse return-shape summary, and one sentence about persistence. Every sentence carries useful information with no filler.

  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 zero-parameter observability tool with an output schema, the description is complete enough. It explains what the tool does, what it returns, and the cross-process persistence behavior, leaving no critical gap for an agent deciding whether to invoke it.

  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?

  The tool takes zero parameters, so the description has no parameter-level semantics to add. The baseline of 4 applies because no input semantics are needed.

  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 opens with 'observability — Snapshot of in-memory retry counter per tool,' which names a specific verb, a precise resource, and the tool's scope. This clearly distinguishes it from the unrelated sibling tools such as file_convert, telegram_poll, and trade_signal.

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

  Usage Guidelines3/5

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

  The 'observability' prefix and 'Snapshot of in-memory retry counter' imply this tool is for inspecting retry/event status, but the description does not explicitly state when to prefer it over alternatives or mention sibling tools. Usage context is present but left for the agent to infer.

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