Server Quality Checklist

Tool Scores

• obsidian_list_notesA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It explains that the keyword filters by path substring, which adds useful behavioral detail. However, it does not mention what the output contains (beyond the existence of an output schema) or whether it includes notes in subfolders, though for a simple listing tool this is a minor gap.

  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, with a clear front-loaded purpose statement followed by a single parameter explanation. Every sentence earns its place and there is no redundant information.

  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 listing tool with an output schema, the description covers the essential behavior and parameter semantics. It could be improved by explicitly saying 'use this to enumerate all vault notes' or distinguishing from content search, but nothing critical is missing for making a correct call.

  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 schema only says keyword is a nullable string with default null; it provides no description. The description adds real semantic value: keyword is an optional filter and matches 'notes whose path contains this string.' This is exactly the meaning an agent needs to invoke the tool correctly.

  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 states a clear verb ('List') and resource ('markdown notes in the vault'), making the tool's primary function obvious. It does not explicitly distinguish itself from siblings like obsidian_search or obsidian_read_note, but the verb and resource are sufficiently specific to infer the difference.

  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 on when to use this tool versus alternatives such as obsidian_search (for content search) or obsidian_read_note (for reading a single note). The optional keyword filter is described, but no context is given about when listing notes is the right choice.

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

• obsidian_ragA
  3.6/5.0
  Behavior2/5

  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 explains that the tool returns context chunks, but it does not state whether the tool is read-only, whether an index must already exist, what happens when no relevant notes are found, or whether external services are invoked. This is a significant gap for a tool with no annotation support.

  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, well-organized, and front-loaded. The purpose sentence is immediately clear, the usage guidance is brief, and the Args section is direct. No sentence is wasted.

  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?

  An output schema exists, so return-value documentation is less critical. The two parameters are well covered. However, the description omits behavioral context such as indexing prerequisites and does not clarify how this tool relates to sibling tools like `obsidian_search` or `obsidian_index_status`, leaving some ambiguity.

  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: `question` is explained as 'the user's question / content to analyze,' and `top_k` is clarified as 'number of context chunks to retrieve (1-20).' This adds real meaning beyond the schema's type and default fields.

  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 states a specific action and resource: 'Retrieve the most relevant Obsidian notes for `question` and return them as context.' This clearly identifies what the tool does. It does not explicitly distinguish itself from the sibling `obsidian_search` tool, so it falls just short of a 5.

  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 a concrete intended use: 'Use this to analyze a user's message against what is stored in the vault: search first, then reason over the returned context.' This tells an agent when to reach for this tool, though it does not mention when not to use it or name alternatives explicitly.

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

• obsidian_indexA
  3.8/5.0
  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 that it scans the whole vault, builds/refreshes the index, and that force rebuilds even if the index exists. However, it does not mention cost/latency of a full vault scan, whether an existing index is replaced or preserved, or side effects beyond indexing.

  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 with the main purpose. The Args section is clearly separated and every sentence/line contributes meaningful information without redundancy.

  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?

  For a simple one-parameter tool, the description covers the core action and parameter. Since an output schema is present, not describing return values is acceptable. However, it is not complete enough because it omits when to choose this over index_status and does not warn about the potentially expensive vault-wide scan. It is viable but has clear gaps.

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

  Parameters5/5

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

  The schema provides only a boolean default false with no parameter description, so the description must compensate. It does so fully: the 'force' argument is explained as 'rebuild the index even if one already exists,' which adds real semantics beyond the schema.

  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 specific, actionable verb and object: 'Scan the vault and build/refresh the embedding index.' This clearly identifies what the tool does and distinguishes it from siblings like obsidian_index_status (checking status vs building) and obsidian_search/obsidian_rag (querying vs indexing).

  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 on when to invoke this tool versus alternatives. It does not mention checking obsidian_index_status first, nor does it say when a refresh is needed or when a rebuild with force is appropriate. The only implied context is that the tool is for building an index, but no exclusions or alternative routing are provided.

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

• obsidian_read_noteA
  3.9/5.0
  Behavior3/5

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

  With no annotations provided, the description must carry the behavioral burden. It does clearly convey that this is a read operation returning the full text of a note, implying no side effects. However, it does not disclose behavior for missing paths, non-markdown files, encoding, or other edge cases that could affect an agent's 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 extremely concise and front-loaded. The first sentence states the action clearly, and the Args section adds the only necessary parameter detail without any filler or repetition of the schema.

  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 single-parameter read tool with an output schema, the description is nearly complete: it explains what the tool does, what the path means, and provides an example. It is only missing brief mention of edge cases such as nonexistent paths or how it relates to sibling tools, but these are not critical for basic invocation.

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

  Parameters5/5

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

  The input schema only defines 'path' as a string with no description (0% schema coverage). The description fully compensates by explaining that the path is vault-relative, should be a markdown path, and provides a concrete example: 'Projects/MyProject.md'. This gives the agent exactly what it needs to construct a correct argument.

  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 with a specific verb and resource: 'Read the full text of a note from the vault.' The phrase 'full text' helps distinguish this from sibling tools that index, search, or list notes, even though those siblings are not explicitly named.

  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?

  The description gives no guidance about when to use this tool versus alternatives such as obsidian_search, obsidian_list_notes, or obsidian_index. It does not mention exclusions, prerequisites, or a decision process, leaving the agent to infer the appropriate context from the tool name alone.

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

• obsidian_index_statusA
  4/5.0
  Behavior3/5

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

  With no annotations, the description must carry the behavioral burden. It communicates a non-mutating status/report action and names the exact condition evaluated, but it does not disclose edge behavior (e.g., error vs false when index is missing) or explicitly confirm it will not create the index. That 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?

  A single sentence that front-loads the verb and delivers the key facts with no filler, redundancy, or irrelevant detail.

  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 zero-parameter status tool with an output schema, the description states the core purpose sufficiently. It is slightly short of complete because it does not explicitly mention side-effects or preconditions, but complexity is low and the output schema can carry return-value details.

  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 and 100% schema coverage, so there is nothing for the description to add. The zero-parameter baseline is 4; the description correctly avoids inventing parameter details.

  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 ('Report') and a clear resource ('index'), and specifies the exact condition being checked (exists and matches the configured embedding model). This clearly differentiates it from siblings like obsidian_index (creation) and obsidian_search (querying).

  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?

  There is no explicit when-to-use or when-not-to-use statement, nor any named alternative. However, the status-report phrasing and sibling list (obsidian_index, obsidian_search, obsidian_rag) imply it is a readiness check before search/RAG operations, which gives the agent some guidance by inference.

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

• obsidian_searchA
  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 full behavioral disclosure burden. It conveys a read-oriented semantic search returning chunks, which is helpful, but it does not mention operational prerequisites such as whether a vault index must already exist or what happens if semantic search is attempted before indexing.

  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 short, front-loaded with the main action, and uses a tidy Args list. Every sentence and field earns its place with no redundant 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?

  For a two-parameter search tool with an output schema, the description covers the essential invocation contract and result granularity. The main missing context is index dependency and explicit sibling routing, but the core calling information is adequate.

  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 0%, and the description compensates by explaining 'query' as natural language and top_k as the result count with a 1-20 range. This adds meaningful meaning beyond the bare type and default values in the schema.

  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 the verb 'semantically search', the resource 'vault', and the output granularity 'chunks', making the operation specific and easy to distinguish from sibling tools like obsidian_list_notes or obsidian_read_note. This is a clear, well-scoped purpose statement.

  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 semantic-search context is clear, so an agent can infer when this tool is appropriate. However, the description does not explicitly state when to prefer it over siblings such as obsidian_rag or obsidian_list_notes, nor does it provide when-not-to-use guidance.

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

• obsidian_get_configA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It adds a valuable privacy guarantee ('The API key is never returned') and implies read-only behavior through 'Show.' This goes beyond a bare getter description; only minor extras like side-effect confirmation are absent.

  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?

  Two brief sentences, no filler. The primary purpose and contents are front-loaded, and the important security note about the API key is included as a separate concise sentence. Every word earns its place.

  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?

  This is a simple zero-parameter getter with an output schema present. The description names the key fields returned and adds the critical API-key caveat. Nothing needed to invoke it correctly is missing.

  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 is 4. The description adds useful semantic clarity by naming the specific configuration fields returned (vault path, embedding provider/model), helping the agent interpret the output even without parameter details.

  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 the specific verb 'Show' with a clear resource ('current configuration') and names concrete contents ('vault path, embedding provider/model'). This clearly distinguishes it from sibling tools focused on indexing, searching, and note operations.

  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 purpose is so specific that when an agent needs configuration details, this is the obvious tool among the listed siblings. It doesn't explicitly name alternatives or exclusions, but no sibling overlaps with config retrieval, so no additional routing is needed.

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