Server Quality Checklist

Tool Scores

• search_noticesA
  3.7/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It does state the output is a list with titles, procuring unit, and deadlines, which is useful. However, it does not disclose any potential side effects (though search is likely read-only), rate limits, or limitations such as the inability to filter by user/workspace. It provides some behavioral context but leaves gaps for a tool with no annotations.

  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 concise sentences. The first sentence states the core purpose, and the second lists supported features and output. Every sentence earns its place, and the description is easily scannable.

  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?

  With 10 parameters, no output schema, and no annotations, the description provides a high-level overview but lacks depth. It covers the main search capabilities and gives some output structure, but it doesn't mention pagination (top/skip), sorting, or the exact behaviors of filters (e.g., OR logic for CPV). The schema covers those details, but the description would benefit from a note on how results are ordered or a reference to sibling tools for further actions. 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.

  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 mentions several parameter categories (free-text, CPV, time, notice type, procedure type) that map to schema properties, but it does not add any meaning beyond what the schema already provides. It omits mention of parameters like order_by, top, skip, and procurement_type. The description adds no extra value beyond the schema's own descriptions.

  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 starts with a clear verb and resource: 'Hae hankintailmoituksia Hilmasta' (Search procurement notices from Hilma). It lists specific filtering capabilities (free-text, CPV, time, notice type, procedure type) and return fields (titles, procuring unit, deadlines). This clearly distinguishes it from sibling tools like get_notice_full and get_expiring_soon, which target individual notice retrieval or time-specific lists.

  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 as a search tool by detailing its filtering and listing behavior, but it does not explicitly state when to use it over alternatives or exclude any use cases. It neither mentions sibling tools nor provides when-not-to-use guidance. Context is clear but not explicit regarding selection among siblings.

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

• get_notice_summaryA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It discloses that it uses the search API, requires no separate subscription, and returns a defined set of metadata fields. It does not explicitly state side-effect-free behavior or auth requirements, but the read-oriented language and return list give useful context.

  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 compact two-sentence statement. It is front-loaded with the action and resource, and each sentence contributes value without redundancy.

  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 one-parameter retrieval tool, the description covers the key aspects: what it returns (all metadata fields listed) and the underlying API usage. There is no output schema, but the return description compensates. It could mention that it returns only the summary and not full content, but the tool name and sibling list imply this.

  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 single parameter notice_id is fully described in the schema with its type and meaning. The tool description only repeats that the summary is fetched 'by noticeId', adding no extra semantic details beyond the schema's high coverage.

  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 fetches a single notice summary using notice_id. The verb 'Hae' and resource 'yksittäisen ilmoituksen yhteenveto' distinguish it from sibling tools like get_notice_full and search_notices.

  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 indicates it is for retrieving a summary of one notice, and notes it uses the search API without requiring a separate order. However, it does not explicitly compare with alternatives like get_notice_full or specify when to choose one over the other, so guidance is only implied.

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

• get_expiring_soonA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It discloses the sorting order (ascending deadline) and the filtering logic, but it does not explicitly state that the operation is read-only, nor does it mention return format or potential edge cases. This is adequate for a simple get tool but lacks deeper behavioral disclosure.

  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 concise sentences: purpose, sorting behavior, and usage examples. It is front-loaded with the primary function and contains no filler or redundancy.

  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 filtered-list tool with no output schema, the description covers the essential aspects: what it returns, how it sorts, and when to use it. It lacks explicit edge-case handling (e.g., no results) but is otherwise complete for the tool's complexity.

  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%, with 'days' and 'cpv_codes' already well described. The tool description does not add any extra meaning beyond what the schema provides, so it meets the baseline but does not exceed it.

  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 retrieves notices with deadlines within N days, using the specific verb 'get' and resource 'notices'. It distinguishes from sibling tools by focusing on expiring deadlines, sorting by deadline ascending, which is not covered by summary/full/search tools.

  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 provides concrete example queries ('what deadlines are next week', 'most urgent projects') and states the sorting behavior, establishing clear context for use. However, it does not explicitly mention alternatives or when not to use it, so it falls short of a 5.

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

• get_notice_fullA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the transparency burden. It discloses the requirement for a separate avp-read-eforms-api subscription and HILMA_READ_API_KEY, which is valuable. It also specifies the output format (eForms XML). It does not mention side effects, error handling, or explicitly confirm read-only behavior, but these are reasonably inferred from a 'get' operation.

  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 sentences, each earning its place: purpose, requirement, and registration URL. It is front-loaded with the main purpose and is concise without unnecessary verbosity.

  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 retrieval tool with no output schema, the description is fairly complete. It explains the return format (eForms XML), contents (contacts, links), and authentication requirements. It does not exhaustively list every field or error scenario, but the tool's simplicity and sibling context (summary vs full) make it sufficient.

  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 provides full coverage for the single parameter notice_id, including a description. The tool description does not add further parameter details, but none are necessary given the 100% schema coverage. Thus the baseline of 3 applies.

  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 retrieves a notice's full details in eForms XML format, including specific contact fields (BT-502, BT-503, BT-506) and portal links. This distinguishes it from sibling get_notice_summary, which likely provides a summary. The verb 'Hae' (get) and the resource 'ilmoituksen' (notice) are explicit.

  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 context for when to use the tool: when full eForms XML data is desired, and it notes a critical prerequisite (separate subscription and API key). However, it does not explicitly mention alternatives or when not to use it, though the context strongly implies the need for full versus summary data.

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