Server Quality Checklist

Tool Scores

• compare_coverageB
  3.4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the behavioral disclosure burden. It does add meaningful behavior by stating that the tool 'groups current matching headlines by paper' and implies a live 'right now' scope. It does not mention any caveats such as source coverage limits, matching semantics, or whether the operation is read-only.

  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 two tight, front-loaded sentences with no filler. The first sentence states the purpose and scope, and the second explains the grouping behavior and the practical value for the agent.

  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 one-parameter read/comparison tool with an output schema provided, the description is largely complete: it covers the main behavior and typical use case while leaving return-format details to the output schema. The main missing pieces are explicit sibling differentiation and precise semantics around 'current' and 'topic', but those are already reflected in other dimension scores.

  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?

  The input schema has only a required string 'topic' with zero description coverage, so the description must compensate. It only restates that the tool is about 'a topic', providing no format, examples, or matching guidance. This is a weak contribution below the baseline needed for a schema with no parameter documentation.

  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 identifies a comparison action over news coverage, grouping current matching headlines by newspaper and exposing framing differences. It does not explicitly name sibling tools for contrast, but the core purpose and resource are unmistakable.

  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 says it is useful for spotting who is running a story, who is ignoring it, and how the angle differs, which implies a comparative use case. However, it never states when to prefer compare_coverage over siblings like scan_news or deep_search, and it gives no exclusions.

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

• deep_searchA
  4.1/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the behavioral disclosure burden. It adds useful constraints — the search is limited to Prothom Alo and covers a large archive — but it does not mention return behavior, pagination, rate limits, or access requirements. It is adequate but not rich.

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

  Conciseness5/5

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

  Three short sentences with no filler. The core action is front-loaded, the scope limitation follows, and the sibling alternative is stated efficiently.

  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 search tool with an output schema, this is nearly complete: scope, limitation, and sibling routing are all covered. It does not describe the return format, but the existence of an output schema reduces the need for that.

  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 does not explain the 'query' or 'limit' parameters beyond their names. The phrase 'full archive' hints at query scope, but it does not compensate for the lack of parameter documentation.

  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 ('Search') and resource ('Prothom Alo's full archive'), making the tool's purpose immediately clear. It also explicitly distinguishes itself from scan_news by noting that this tool covers only Prothom Alo.

  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 explicitly tells the agent when not to use this tool and which sibling to use instead: 'For current coverage across every paper, use scan_news instead.' It also explains why, because only Prothom Alo exposes a searchable API.

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

• scan_newsA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the full behavioral burden and does well: it explains recency ordering, keyword matching behavior (case-insensitive, Bengali), and sources default behavior. It implies a read-only scan and does not mention edge cases like empty results or pagination, but the provided behavior is substantially 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 concise, well-structured, and front-loaded with the core purpose. Each paragraph earns its place by covering the main behavior, keyword semantics, and sources option without unnecessary 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 output schema exists, return values need not be described. The description covers the main use case, filtering behavior, and sources. It is slightly incomplete in not clarifying how this tool relates to deep_search or compare_coverage and in omitting limit semantics, but overall it is sufficient for an agent to call it correctly.

  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 explaining keyword and sources in meaningful detail. It does not explain the limit parameter, though 'limit' with a default of 20 is reasonably self-explanatory from the schema. Overall, it adds strong semantics for two of the three parameters.

  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 the tool scans the latest articles across Bangladeshi newspapers, newest first, and explains the keyword filtering use case. However, it does not explicitly differentiate from sibling tools like deep_search or compare_coverage, so the distinction is mostly implied rather than stated.

  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 clear usage context: use keyword to check whether a brand, person, or topic is being covered right now, and use sources to limit coverage. It also points to list_sources for available options, but it does not provide explicit when-not-to-use guidance or compare against deep_search/compare_coverage.

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

• list_sourcesA
  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 behavioral burden. It clearly indicates a read-only listing operation and adds meaningful nuance that the response includes both covered and deliberately excluded newspapers. This goes beyond the title and gives the agent a fuller picture.

  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?

  A single, front-loaded sentence communicates the full scope without any wasted words. Every element earns its place and the deliberate-exclusion detail is added efficiently.

  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?

  Given the tool's simplicity, zero parameters, and available output schema, the description is complete. It tells the agent exactly what will be returned without needing to cover return-value formatting.

  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 has zero parameters, so the baseline of 4 applies. The description does not need to explain parameter semantics because there are none to clarify.

  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 uses a specific verb ('List') and resource ('newspapers this radar covers'), and explicitly distinguishes itself by also including deliberately excluded sources. This makes the tool's purpose clear even among siblings like scan_news and deep_search.

  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 when to use the tool—when you need the radar's source list—but does not explicitly contrast it with siblings or state when not to use it. There are no exclusions or alternative routing clues.

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