Server Quality Checklist

Tool Scores

• deleteB
  3.2/5.0
  Behavior2/5

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

  The description states that the tool deletes a note and returns confirmation or error, but it does not disclose implications of the destructive action, such as permanence, recursive behavior, or required permissions. With no annotations, this is insufficient for a destructive 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 concise and well-structured, with the action front-loaded and separate sections for args and returns. Every sentence serves a purpose without unnecessary elaboration.

  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 low-complexity delete operation, the description covers the core action and parameter, but lacks crucial behavioral details like whether deletion is permanent, if it affects linked notes, or any recovery mechanism. Given the destructive nature, more context would be expected despite the simple interface.

  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 description explains that 'path' is relative to the vault, adding meaningful context beyond the bare schema. Since the schema has no description for this parameter, this compensation is valuable and adequate for a single-parameter tool.

  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 action 'Supprime une note' (deletes a note), which is a specific verb and resource. It is distinct from sibling tools like move or clear, though it does not explicitly differentiate them. The purpose is unambiguous.

  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?

  No guidance is provided about when to use this tool versus alternatives. It simply describes the action without any mention of prerequisites, exclusions, or situations where another tool would be more appropriate.

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

• similarB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, and the description does not disclose side effects, permissions, or dependencies such as indexing. It only mentions return values, leaving behavioral expectations largely unspecified.

  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: a one-line purpose followed by clear Args and Returns sections. Every sentence serves a purpose with no fluff or excessive 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 simple tool with 2 parameters and an output schema, the description provides adequate purpose, parameters, and return type. It lacks context on prerequisites (e.g., whether notes must be indexed) but is not incomplete enough to significantly hinder 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 coverage is 0%, but the description explains both parameters: path (source note path) and top_k (number of results, default 5). This compensates for the schema's lack of descriptions, though the explanations are minimal and slightly redundant with the schema.

  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 finds semantically similar notes, which is a specific action on resources. It does not explicitly differentiate from sibling tools like search or backlinks, but the semantic similarity scope is distinct and understandable.

  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?

  No guidance is provided on when to use this tool versus alternatives. The description only explains what it does, without mentioning use cases, prerequisites, or exclusions.

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

• writeB
  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 burden of explaining behavior. It does disclose the three modes (create, replace, append) and the auto_index behavior, which adds context. However, it does not warn about data loss in 'replace' mode, mention file permissions, or describe side effects such as creating intermediate directories, leaving the agent with incomplete behavioral transparency.

  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 well-structured: a one-line summary, a compact parameter list, and a minimal return description. Every sentence adds value, with no fluff or repetition of the schema.

  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 moderate complexity of the tool, the description covers the parameters and basic return behavior, and an output schema exists. However, it lacks broader context, such as when to choose this over alternatives or edge-case behavior (e.g., creating a note that already exists, handling invalid paths), leaving the agent with an adequate but incomplete picture.

  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 input schema has zero descriptions (0% coverage), so the description compensates well by explaining each parameter: path, content, mode with its three possible values, and auto_index with its default. It even clarifies that path is relative to the vault, adding useful semantic detail.

  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 creates or modifies a note ('Cree ou modifie une note'), which distinguishes it from sibling tools like read, delete, or move. However, it does not explicitly differentiate from potential update-like tools or explain why one would use this over alternatives.

  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. The description only explains how the tool works (modes, auto_index) but does not indicate that it should be used for creating, replacing, or appending note content, nor does it mention any prerequisites or exclusions.

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

• moveA
  3.5/5.0
  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 only mentions returning a confirmation or error, but does not disclose whether the operation can overwrite existing files, whether links/backlinks are updated, or any destructive risks. This is a significant gap for a file operation that changes the location of a note.

  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 exceptionally concise and well-structured, with clear sections for arguments and return value. It front-loads the main purpose and avoids any redundant wording, earning its place in every sentence.

  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 move/rename operation, the description covers basic arguments and output, but omits critical operational details such as overwrite behavior, impact on internal references, and filesystem constraints. The presence of an output schema reduces the need for return documentation, yet the description still lacks sufficient context for safe and correct use.

  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 description provides brief semantics for both parameters—'Chemin actuel de la note' and 'Nouveau chemin'—which adds value over the schema's minimal 'Old Path'/'New Path' titles. However, it does not specify path format (absolute vs relative), file name rules, or directory behavior. With 0% schema coverage, the description partially compensates but remains incomplete.

  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's function with the verbs 'Déplace' (move) and 'renomme' (rename) and the resource 'une note' (a note). This distinguishes it from sibling tools such as read, write, and delete.

  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 for moving or renaming notes but does not explicitly state when to prefer this tool over alternatives or mention any prerequisites. It lacks explicit when-to-use or when-not-to-use guidance, relying on the tool's name and verb to convey context.

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

• searchA
  3.7/5.0
  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 that the search is 'hybrid' and states the return format (title, excerpt, score), which is useful. However, it does not explicitly mention whether it is read-only, any permission requirements, or potential limitations like pagination, leaving some behavioral gaps.

  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 well-structured, with a brief intro followed by clear Args and Returns sections. Every sentence serves a purpose, 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?

  The description covers all essential elements: parameters with defaults, filters, and the return structure. Given the simplicity of the tool, it is nearly complete, but the absence of usage guidance and explicit safety/read-only context prevents a perfect score.

  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 has no parameter descriptions (coverage 0%), but the tool description compensates fully by explaining each parameter: query, top_k, folder filter, and tags (including comma-separated format). This adds clear meaning beyond the titles and defaults, making it highly valuable for correct usage.

  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 'hybrid semantic search in the Obsidian vault' with a specific verb and resource, clearly indicating the tool's function. It distinguishes from siblings like 'similar' by being query-based, but does not explicitly name alternatives or contrast with other search-related tools, so it stops 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 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. The description simply explains what the tool does and its parameters, but does not mention when this search is preferred over 'similar' or other sibling tools, nor any exclusions.

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

• indexA
  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 adds useful behavioral context by explaining the same-process advantage and cache implications, and distinguishes full vs incremental indexing. However, it does not disclose potential side effects, permission requirements, or performance costs of a full reindex.

  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 lean and well-structured: a short summary, a rationale sentence, and straightforward Args/Returns sections. The Returns line is vague, but since an output schema exists, this is acceptable and does not bloat the text.

  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 tool with an output schema, the description covers purpose, the main behavioral choice (full/incremental), and even gives rationale about process/cache isolation. It lacks explicit guidance about how this tool relates to sibling tools like refresh or clear, but overall it is sufficient.

  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 has 0% description coverage, so the description must compensate. It fully explains the only parameter: 'full' semantics are described as reindexing the entire vault versus incremental indexing, adding clear meaning beyond the raw schema.

  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 ('Indexe les nouvelles notes') and identifies the target resource (the vault via MCP server). It also differentiates from the CLI approach, but does not explicitly distinguish the tool from sibling tools like refresh or reload, so it falls 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 gives explicit usage context: it is preferred over the CLI because it runs in the same process and avoids ChromaDB cache issues. However, it provides no exclusions or comparisons to alternative sibling tools, so guidance is clear but not fully complete.

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

• refreshA
  4/5.0
  Behavior2/5

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

  No annotations are provided, so the description must disclose behavioral traits. It states the action (refreshes index) and return value, but does not clarify if this is a destructive or safe operation, nor any side effects or prerequisites beyond the indexing step. The description carries the full burden but only partially fulfills it.

  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 serving a purpose: the first states the core function, the second gives usage context, and the third describes the return value. It is front-loaded and avoids unnecessary 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 simple zero-parameter tool with an output schema, the description is generally complete: it specifies the trigger (after indexing), the effect (refresh BM25 index), and the return (confirmation with count). It could be slightly more explicit about the side-effect nature, but overall it is sufficient for an agent to use 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?

  The tool has zero parameters, so baseline is 4. The description does not need to explain parameters; the schema is empty and coverage is 100%, aligning with the baseline.

  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's function: 'Rafraichit l'index BM25' (refreshes the BM25 index) after indexing new notes. It identifies a specific resource (BM25 index) and implies a distinct purpose from siblings like 'index' and 'reload' by focusing on post-indexing refresh for hybrid search.

  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 explicitly tells when to use the tool: 'Appeler apres avoir indexe de nouvelles notes via le menu CLI' (call after indexing new notes). This gives clear contextual usage, though it does not mention alternatives or situations where the tool should not be used.

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

• backlinksA
  4.2/5.0
  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 of behavioral disclosure. It indicates a read-only retrieval operation ('Trouve') and includes a Returns line, but it does not disclose edge-case behavior such as invalid paths, empty results, or side effects (though none are expected). The coverage is basic but sufficient for a simple read 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 concise, with a single purpose sentence followed by clearly labeled Args and Returns sections. Every sentence provides necessary information, and the structured format (Args/Returns) makes it easy to parse.

  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 (one parameter, straightforward purpose) and the presence of an output schema, the description is complete. It names the argument, explains its meaning, and states what the result is (list of notes with backlinks). No critical information is missing for an agent to use the tool correctly.

  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 the property name 'path' with a type string and no description (coverage 0%). The description's Args section clarifies that 'path' accepts either a chemin (path) or a titre (title), adding crucial semantic meaning that the schema lacks. This fully compensates for the zero schema 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 action ('Trouve' = finds) and the resource ('les notes qui pointent vers cette note' = notes that point to this note), unambiguously identifying it as a backlink lookup tool. This is distinct from sibling tools like 'similar' (content similarity) and 'search' (text 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 its usage by stating its function (finding backlinks), but it does not explicitly mention when to use it over alternatives or provide exclusions. There is no 'when not to use' guidance, so it is minimally adequate but lacks explicit differentiation from sibling tools.

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

• listA
  4.2/5.0
  Behavior3/5

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

  Since no annotations are provided, the description must explain behavior. It discloses that the tool returns a list of notes with titles and tags, and that it supports filters. However, it does not explicitly state that the operation is read-only or that it does not modify the vault. For a simple list operation this is acceptable, but the lack of an explicit safety statement leaves some ambiguity.

  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 well-structured: a one-sentence summary, a clear Args section, and a Returns section. Every sentence adds value, and the structure makes the information easily scannable. There is no redundancy or irrelevant detail.

  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 list tool with three optional parameters, the description covers all essential aspects: purpose, parameter semantics, and return format. The existence of an output schema further clarifies return values, and the description's mention of 'titre et tags' aligns with typical schema. No major gaps are apparent.

  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 has no descriptions for parameters (0% coverage), so the description compensates fully. It explains each parameter: folder filtering with '/' for root, tags as comma-separated, and limit with its default of 50. It also clarifies optionality and behavior, providing 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 clearly states the tool's function: 'Liste les notes du vault' (list vault notes). It specifies the resource (notes) and the action (list), making it unambiguous. Although it does not explicitly compare to siblings like 'search', the verb 'list' and the mention of filtering by folder/tags distinguish it as a bulk listing operation rather than a text 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 usage by explaining the tool's filtering capabilities, but it does not explicitly state when to use this tool over alternatives like 'search' or 'read'. There is no mention of 'use this for listing all notes' or 'use search for full-text queries'. The context is clear enough for an agent to infer, but explicit exclusions or alternatives are missing.

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

• readA
  4.2/5.0
  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 disclosing behavior. It states that the tool returns the note content with frontmatter, tags, and links, which adds useful context. However, it does not reveal potential error behavior (e.g., missing file), permissions, or whether it is strictly read-only beyond the name 'read'. This is minimal but sufficient for a simple read 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 very concise: a short purpose statement followed by Args and Returns sections. Every sentence contributes useful information without redundancy. The structure is front-loaded with the primary purpose, making it easy for an agent to quickly understand the tool.

  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 (one parameter, no annotations), the description covers the essential aspects: purpose, parameter semantics, and return value. An output schema exists, so the description does not need to fully specify return fields. It lacks details on error cases, but these are less critical for a basic read operation and do not prevent correct 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?

  The schema description coverage is 0%, so the description must compensate. It does so by explaining the meaning of 'path': 'Chemin de la note (relatif au vault ou absolu)' (relative to the vault or absolute). This adds meaningful guidance beyond the schema's bare field name and type, effectively documenting the only 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 states the tool's function: 'Lit une note avec ses metadonnees' (Reads a note with its metadata). It specifies both the verb ('lit') and the resource ('note'), and the inclusion of metadata further clarifies the scope. This distinguishes it from sibling tools like 'write', 'delete', and 'move', which have obviously different purposes.

  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 clear context for when to use the tool: to read a note with its metadata. It does not explicitly state when not to use it or mention alternatives, but for a simple read operation the intended usage is evident. This aligns with a 'clear context, no exclusions' rating.

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

• reloadA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries full burden. It discloses that the tool 'Reinitialise ChromaDB, les embeddings, le retriever et le graphe', indicating a resets state. Still, it does not mention whether this destroys data, if it is safe to run concurrently, or if special permissions are needed, leaving room for ambiguity.

  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 and well-structured: it starts with the main purpose, then lists specific components that are reset, includes a usage note, and ends with the return value. Every sentence adds meaningful information 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 tool with no parameters and no annotations, the description covers the action, the affected components, and the expected return value. However, it does not explicitly differentiate from sibling tools like 'refresh' and 'clear', which could be ambiguous in agent contexts. It addresses 'index' only, leaving other potential alternatives unclear.

  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 (schema is empty), so the description doesn't need to explain parameter semantics. The description adds no parameter information, but with 0 params this is satisfactory; baseline is 4.

  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's function: 'Recharge completement tous les caches et connexions' and 'Reinitialise ChromaDB, les embeddings, le retriever et le graphe.' It uses specific verbs (recharge/reinitialise) and resources, and distinguishes from the 'index' tool via the note, making its purpose unambiguous.

  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 an explicit alternative: 'Preferer l'outil index pour indexer de nouvelles notes, car il evite les problemes de cache inter-processus.' This tells the agent when not to use reload and suggests a better alternative. However, it doesn't cover other potential competing tools like 'refresh' or 'clear', so guidance is limited but clear for the indexing case.

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

• clearA
  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 full burden. It clearly discloses the destructive nature of completely emptying the database and graph, and notes a required follow-up action (index(full=True)). It does not warn about irreversibility or permissions, but the language strongly implies total removal, making the behavior 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 concise: three sentences that front-load the main action, then add use case, follow-up, and return value. Every sentence earns its place with no fluff or repetition.

  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 destructive tool with no parameters and an output schema, the description is complete. It states what the tool does, why/when to use it, the required post-action, and what it returns. No key information 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 takes no parameters (schema is empty), so the baseline for parameter semantics is 4. The description adds no param info but doesn't need to, as there are none to explain.

  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 empties the entire ChromaDB base and graph ('Vide completement la base ChromaDB et le graphe'), giving a specific verb and resource. It distinguishes itself from siblings like 'delete' by emphasizing complete clearing, and the purpose is unambiguous.

  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 explicit when-to-use guidance: 'Utile pour nettoyer les documents orphelins ou repartir de zero' (useful for cleaning orphaned documents or starting from scratch). It also instructs to call index(full=True) afterwards. However, it doesn't explicitly state when not to use it or mention alternatives like 'delete' for targeted removal, so it's not a perfect 5.

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