Server Quality Checklist

Tool Scores

• memory_timelineB
  3.1/5.0
  Behavior3/5

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

  With no annotations, the description bears the burden of behavioral disclosure. 'View' and 'chronological timeline' imply a read-only listing, which is helpful, but no details are given about ordering direction, result format, pagination, or whether any side effects occur.

  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, well-structured sentence that front-loads the main action and resource. Every word contributes value, and it includes useful examples of the operation types shown.

  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 read-only timeline with one optional parameter, the description is mostly adequate. However, the lack of sibling differentiation, no mention of the `limit` parameter, and no output format details leave clear gaps for an agent deciding how to invoke it.

  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 single parameter `limit` has zero schema description coverage and the tool description does not mention it at all. While the parameter is somewhat self-explanatory from its name and default value, the description adds no meaning beyond 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 states a specific verb ('View') and a clear resource ('recent memory operations') with examples of operation types. It is sufficiently clear that this is a timeline of memory operations, though it does not explicitly distinguish itself from the similarly named sibling 'memory_history'.

  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 provides no guidance on when to use this tool versus siblings like `memory_recall` or `memory_history`, nor does it mention any alternative conditions. Usage context is only implied by the word 'View'.

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

• memory_historyB
  3.2/5.0
  Behavior2/5

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

  There are no annotations, so the description carries the full burden of behavioral disclosure. It only indicates a read-style operation ('View') and says nothing about the shape of the returned history, ordering, pagination, or how 'previous edits' are represented.

  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 a single, front-loaded sentence with no filler. It is easy to parse and economical, though it may be too terse to convey all necessary behavioral and parameter guidance.

  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 read tool, the description names the resource and indicates the action, and the required title parameter is sufficient to invoke it. However, with no output schema and no annotations, the lack of return-format and limit semantics leaves clear gaps for an agent trying to use the results correctly.

  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 title parameter is already documented in the schema, but the limit parameter has no description and the tool description adds no meaning for it. With 50% schema coverage, the description needed to compensate for the undocumented parameter and did not.

  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 verb ('View') and a precise resource ('version history of a specific memory note'), with the clarifying parenthetical 'previous edits'. It is immediately clear what the tool does, but it does not explicitly contrast with sibling tools such as memory_timeline or memory_audit.

  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 conveys a clear use case: checking the previous edits of one specific note. It gives enough context for when an agent should invoke it, though it provides no explicit exclusions or alternative routing to sibling tools.

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

• memory_recallB
  3.2/5.0
  Behavior3/5

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

  With no annotations, the description carries the behavioral burden. It discloses that the tool retrieves from both private and shared stores and that search can be semantic, keyword-based, or graph-based. However, it does not mention return format, whether any filtering or ranking applies, or any access caveats.

  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 concise sentence with no filler. The primary action and retrieval scope are front-loaded, making it easy to parse quickly.

  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?

  Given 5 parameters, a nested scope object, no output schema, no annotations, and several related sibling tools, this description is too sparse. It leaves important invocation details such as mode defaults, query semantics, shared-memory handling, and result expectations unexplained.

  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 only 40%, and the description compensates poorly. It loosely maps to the mode enum with 'semantic meaning, keywords, or graph' and mentions shared/private stores, but it does not clarify the required query parameter, the meaning of hybrid mode, top_k behavior, or the nested scope object.

  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 uses a specific verb and resource: 'Search memory' and lists search methods (semantic, keyword, graph). It is clear about what the tool does, though it does not explicitly differentiate itself from sibling tools like memory_timeline or memory_history.

  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 the tool is for searching/recalling stored memories, but it gives no explicit guidance on when to prefer memory_recall over alternatives like memory_assemble_context, memory_timeline, or memory_remind_me. Usage context is inferred rather than stated.

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

• memory_remind_meB
  3.2/5.0
  Behavior2/5

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

  Because no annotations are provided, the description carries the full burden of behavioral disclosure. It only states the basic scheduling action and omits important traits such as trigger_at format, how recurrence is applied, side effects when the reminder fires, and whether a memory entry is also created.

  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 a single efficient, front-loaded sentence with no wasted words. However, its brevity comes at the cost of necessary parameter and behavior details, so it is concise but not fully appropriately sized.

  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?

  For a tool with four parameters, no annotations, schema description coverage of 0%, and no output schema, this description is too thin. An agent cannot confidently determine how to provide trigger_at or how recurring should behave, so the definition is materially incomplete.

  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%, so the description must compensate, but it names no parameters directly. It only hints at 'future' and 'recurring', leaving title, content, trigger_at format, and the relationship between recurring and trigger_at undocumented.

  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 ('Schedule') and identifies the resource ('future reminder or recurring task'). This clearly distinguishes it from retrospective siblings like memory_recall, memory_timeline, and memory_history, and from memory_remember which implies storage rather than scheduling.

  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 phrase 'Schedule a future reminder or recurring task' implies the core use case, but no explicit guidance is given about when to choose this over alternatives. There are no prerequisites, no exclusions, and no mention of sibling tools that might be more appropriate.

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

• memory_auditA
  3.5/5.0
  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 behavioral disclosure. The verb 'Get' strongly implies a read-only operation, and the listed outputs suggest no mutation. However, it does not explicitly state that no state changes occur, whether permissions are required, or whether the health check performs any active diagnostics.

  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, compact sentence with no filler. The verb is front-loaded and each listed item contributes meaning. Every word earns its place, and the structure is easy for an agent to parse quickly.

  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?

  With zero parameters and no output schema, the description needs to convey what the tool returns. It does so by listing four output categories: statistics, health check, active wings, and version info. This is adequate for simple invocation, though the term 'active wings' is domain-specific and not expanded.

  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 schema provides no parameter documentation. Per the baseline for a zero-parameter tool, the description does not need to compensate for parameter gaps; it simply describes the operation's outputs, which is sufficient.

  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 opens with the specific verb 'Get' and names distinct resources: memory system statistics, health check, active wings, and version info. This makes the tool's focus clear and differentiates it from content-oriented siblings like memory_recall or memory_history, though it does not explicitly contrast itself with them.

  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 choose memory_audit over sibling tools. While the system-level subject matter implies a diagnostic use case, the description does not explicitly state when to run an audit versus when to use memory_history, memory_timeline, or memory_assemble_context.

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

• memory_publish_sharedA
  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 behavioral burden. It discloses that this is a write/publish action with cross-agent visibility and imposes a sanitization constraint, which is valuable. However, it does not mention persistence, overwrite/append behavior, permissions, or what the call returns.

  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 with no filler. The action, object, and destination are stated directly, and every word adds meaning.

  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?

  For a writing tool with five parameters, no annotations, and no output schema, this description is too thin. It omits expected call semantics such as return value, success/failure behavior, and the meaning of room/wing, leaving an agent to guess at important usage details.

  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 schema already documents title, content, and tags, but room and wing are undocumented and the description does not clarify them. The general phrase 'finding or policy' adds only minimal semantics to the content parameter and says nothing about how the publish target or routing fields behave.

  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 a specific verb ('Publish'), a concrete object ('a sanitized, curated finding or policy'), and a precise destination ('cross-agent shared fleet memory'). This clearly differentiates it from local memory tools in the sibling set such as memory_remember or memory_recall.

  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?

  It implies the occasion ('sanitized, curated' material meant for shared use) but never explicitly says when to prefer this over memory_remember or memory_ingest_session, nor does it provide when-not-to-use exclusions. The shared-fleet scope is useful context, but the routing guidance is left to inference.

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

• memory_assemble_contextA
  3.7/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full behavioral burden. It discloses that the tool retrieves rather than mutates, filters for 'high-salience', enforces a 'strict token-budget', and formats into XML. This is useful, though it doesn't explain how salience is determined or how failures/token-truncation are handled.

  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 dense, front-loaded sentence with no filler. It names the primary action, the input type, the processing behavior, and the output format in an efficient structure.

  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 description covers the key output (XML prompt block) but leaves important gaps for a tool with five parameters and no annotations: the meaning of each `mode`, how `scope` is applied, the effect of `include_shared`, and expected behavior when the token budget is exceeded. The schema fills some gaps, but the description alone isn't fully complete for correct invocation.

  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 80%, so the schema already documents most parameter meanings. The description adds some context around token budgeting and salience, but it doesn't elaborate on the `mode` enum, `scope` object, or `include_shared` flag beyond what the schema fields already say. This is adequate but not additive.

  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 ('Retrieve and format') and resource ('high-salience memories'), and specifies the unique output format: 'strict token-budgeted XML prompt block ready for direct agent context injection.' It doesn't explicitly name sibling alternatives, but the XML formatting and context-injection purpose distinguish it from tools like memory_recall or memory_timeline.

  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 intended use is implied: assemble memory context for direct agent injection. It does not name when to use this over alternatives, nor provide any when-not-to-use guidance. The phrase 'ready for direct agent context injection' gives some context, but an agent would need to infer the comparison with memory_recall.

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

• memory_ingest_sessionA
  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 behavioral disclosure burden. It usefully disloses that content is stored verbatim and split by turn boundaries, but it does not explain side effects, storage semantics, deduplication, limits, or whether repeated ingestion creates duplicates. These would be valuable for a memory-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?

  One sentence, no filler, and the most decision-relevant information is front-loaded. The phrase about splitting along turn boundaries is efficiently included without bloating the description.

  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 ingestion tool, the core invocation path is clear: provide the full transcript. However, no output schema or annotations exist, and the optional room/wing parameters are unexplained, so an agent would need to infer their purpose from names or defaults. This leaves some contextual ambiguity around storage targeting.

  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 only 33%, with only 'transcript' having a schema description. The description adds meaning to the requied parameter by specifying 'verbatim' and 'split along conversational turn boundaries', but it does not explain the optional 'room' and 'wing' parameters, which remain defined only by their names and defaults.

  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 identifies the action ('Ingest'), the resource ('full conversation transcript'), the destination ('into memory'), and the precise behavior ('verbatim, split along conversational turn boundaries'). This distinguishes it from sibling tools like memory_remember or memory_recall, which likely handle individual memories rather than bulk ingestion.

  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 this is for full multi-turn conversation transcripts, which suggests a bulk ingest use case distinct from memory_remember or memory_recall. However, it does not explicitly state when not to use it or name alternative tools, leaving any routing decision to inference.

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

• memory_rememberA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden and it does add useful behavioral context: 'private,' 'vault,' 'semantic embedding,' and hierarchy. It does not disclose behaviors such as duplicate-title handling, temporal decay, or return value, which leaves some opacity for a state-changing 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?

  One sentence, front-loaded with the verb, and every detail—privacy, vault, embedding, tags, scope—earns its place. There is no filler or 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?

  Schema plus description covers what to pass, but the absence of annotations and output schema, combined with seven sibling tools, leaves gaps: no routing guidance versus ingestion/sharing tools and no statement of what happens on success or when a title already exists. Complete enough for basic invocation but not fully self-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?

  Schema description coverage is 100% and each parameter already has meaningful descriptions (e.g., room is 'Topic within the wing'; pinned explains Ebbinghaus decay). The description adds only the notion of hierarchy, not substantive parameter semantics, so the 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 states a specific action ('Store') and a specific resource ('private memory note in the vault') while naming key processing details: semantic embedding, tags, and hierarchical wing/room scope. 'Private' distinguishes it from shared publication, and the write verb separates it from retrieval siblings like memory_recall.

  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?

  Usage is implied by the store verb: use this when saving a private memory note. However, the description provides no explicit when-to-use or when-not-to-use guidance and names no alternatives, so an agent must infer the boundary against siblings like memory_ingest_session and memory_publish_shared.

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