Server Quality Checklist

Tool Scores

• search_knowledgeB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only states that the tool searches a RAG knowledge base; it does not mention whether results are ranked, whether it is read-only, what types of queries are supported, or any rate/access considerations. The verb 'search' implies a non-mutating operation, but little else 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 a single, front-loaded sentence with zero wasted words. It states the operation and the target surface directly. It is appropriately concise for the tool's simplicity.

  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?

  With no output schema, the description should give some indication of return values or result behavior, but it does not. It also lacks guidance on user_id scoping or how limit affects results. Given the 3-parameter search tool and no annotations, this description is too sparse to fully equip an agent to use the tool correctly in varied contexts.

  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 adds that the search targets the OpenMemory RAG knowledge base, giving the query parameter contextual meaning, but it does not explain limit or user_id semantics beyond their schema descriptions. The description adds marginal context but does not compensate beyond the baseline.

  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 'Search the OpenMemory RAG knowledge base' uses a specific verb and resource, clearly indicating this tool performs retrieval on a knowledge base. It is readily distinguishable from the import_* siblings, though it does not explicitly name them. Slightly vague about what type of content is searched, but otherwise clear.

  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 retrieval, and the sibling import tools imply this is the search counterpart. However, there is no explicit guidance on when to prefer this over allernate approaches, no exclusions, and no mention of user_id filtering or limit usage. Usage context must be inferred from the tool name and schema.

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

• import_textA
  3.7/5.0
  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. It conveys that the operation mutates the knowledge base by importing content, but does not disclose permission requirements, deduplication or overwrite behavior, idempotency, or the response shape. This is a noticeable gap for a mutating 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?

  A single eight-word sentence that front-lods the action and resource with no filler. It is appropriately sized for a straightforward import operation, though some behavioral context was traded away in favor of brevity.

  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 four-parameter import tool with no output schema and no annotations, the description provides the core purpose and destination. The schema covers parameters, but the agent gets no guidance on return values, duplicate handling, or multi-user scoping via user_id. Adequate for a simple call, yet with clear gaps.

  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 coverage is 100%, so the schema already documents all four parameters. The description adds no parameter-specific detail beyond the schema, though 'raw text' loosely maps to the required content field.

  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 ('Import') and identifies the resource ('raw text content') and destination ('OpenMemory RAG knowledge base'). The modifier 'raw text' differentiates it from the sibling tools import_file and import_url, making it clear that this is for direct text ingestion rather than file or URL imports.

  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 phrasing implies the context: use this when you have raw text content to store in the knowledge base. It does not explicitly name alternatives or state when not to use it, but for a simple import tool the intended usage is clear enough.

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

• import_urlA
  3.7/5.0
  Behavior2/5

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

  No annotations are provided, so the description must carry the full burden. 'Import content' implies a write operation, but it does not disclose side effects, idempotency, duplicate handling, network fetch behavior, or any dependencies like authentication. An agent is left guessing what happens after the call.

  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 concise sentence with no filler. Every word contributes to identifying the operation, the source, and the destination. It is front-loaded and 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?

  The tool is simple and all parameters are schema-documented, so the core operation is understandable. However, there is no output schema and the description does not mention return values, success/failure behavior, or post-import state. This leaves meaningful gaps for an agent deciding whether the call succeeded or what to do next.

  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 schema already documents url, tags, and user_id. The description adds no additional parameter-level meaning such as URL format constraints, tag syntax, or how user_id affects routing, so baseline 3 is appropriate.

  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 clear verb ('Import'), a specific resource ('content from a URL'), and a target system ('OpenMemory RAG knowledge base'). This makes the tool's purpose immediately distinguishable from siblings like import_file and import_text by source type.

  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 it: when content is available at a URL. It does not explicitly mention alternatives or exclusions, but the input type is self-evident and the sibling names reinforce the distinction.

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

• import_fileA
  3.9/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of disclosing behavior. It states what the tool does and which file types it supports, but does not explain what happens during the import (e.g., processing, indexing), whether existing documents are updated or duplicated, or how errors and results are returned. For a tool that mutates a knowledge base, this is a significant 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 a single, direct sentence focused on the essential facts: action, target resource, and supported file formats. No unnecessary words or filler. The main idea is front-loaded.

  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 schema documents all three parameters, and the description clarifies the tool's scope and file-type restrictions. However, with no output schema and no annotations, the agent is left without information about the import result, failure behavior, or side effects. It is adequate for a simple import tool but not fully complete.

  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 100%, which gives the baseline 3. The description adds value beyond the schema by listing supported file extensions, which clarifies what file_path values are valid and helps the agent choose appropriate inputs.

  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 ('Import'), the resource ('a local file into OpenMemory RAG knowledge base'), and supported formats (PDF, DOCX, TXT, MD, HTML). The phrase 'local file' distinguishes it from sibling tools import_url and import_text.

  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 makes the usage context clear: this tool is for local file imports, not URL or text imports. It does not explicitly state exclusions or name alternatives, but the sibling tool names and the phrase 'local file' provide enough directional guidance.

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