Server Quality Checklist

Tool Scores

• memory_explainC
  2.8/5.0
  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 disclose behavioral traits. 'Search memory' implies a read-only action, but the description does not explicitly state whether it unmutated or requires permissions, nor does it explain the nature of the diagnostics beyond jargon. The behavioral disclosure is insufficient for a tool with no annotatons.

  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 one concise, front-loaded sentence with no wasted wording or filler. It could use more depth, but that is a completeness issue rather than a conciseness or structure failure.

  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?

  Even though there is an output schema, the description does not establish the key context: why anyone would choose this over memory_search, what "deterministic routing, fusion, and abstention" means in practitioner terms, or what behavioral tradeoffs come. For a specialized diagnostics tool with no annotations or clear parameter docs, this definition is incomplete.

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

  Parameters1/5

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

  Schema description coverage is 0%, so the description needs to compensate for the three parameters explain. 'Query', 'limit', and 'token_budget' are not mentione, and 'token_budget' especially is not self-explaning. The description does not become more contribution for the parameter semantics.

  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 ('Search memory') and a scope ('include deterministic routing, fusion, and abstention diagnostics'), which makes it distinguishable from sibling memory_search. It is clear enough but does not explicitly name or contrast the sibling tools, 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 Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The diagnostics wording implies the tool is for explaining or debugging memory retrieval decisions, but the description never explicitly says when to use this over memory_search, memory_get, or memory_sync, nor does it provide any exclusions or alternatives. Usage guidance is only implied, not stated.

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

• memory_syncB
  3.1/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral detail. It does disclose 'incrementally ingest' and 'atomically update affected indexes', which is useful, but it doesn't explain side effects, failure behavior, permissions, idempotency, or what 'allowed' means in practice.

  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 with no fluff. The core action 'incrementally ingest and atomically update' is clear and front-loaded, and every word earns its place.

  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 no annotations, undocumented parameters, and multiple siblings, it is under-specified. It omits usage direction, parameter semantics, and behavior side effects; the output schema helps but doesn't make up for those gaps.

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

  Parameters1/5

  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 for the paths and adapter parameters. It doesn't name either parameter or explain what paths and adapter expect, nor how they affect synchronization.

  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?

  Clearly specifies a distinct operation: incrementally ingest allowed agent-session roots and atomically update indexes. This distinguishes it from the read-oriented sibling tools memory_search, memory_get, memory_explain, and memory_status.

  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 given about when to call this tool, when not to call it, or how it relates to memory_search and memory_get. The only contexts is inferred from the phrase 'sync', but the description never says when synchronization should be triggered.

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

• memory_getB
  3.2/5.0
  Behavior3/5

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

  With no annotations, the description anues "verify" against its original sourcefile, a non-obvious behavior that says the tool checks correctness and isn't just a raw accessor. It does not state outverification failures, permissions, or side effects, so the behavior is only partially disclosed.

  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 sentence with no wasted or repeated information. It fronts the main action and adds only the verification detail in the second clause.

  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?

  The tool is simple, but missing include_raw semantics and the format/form of a citation means the agent cannot safely choose correct arguments. The output schema may explain return but no the input field, and no annotation compensates.

  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%, and the description only clarifies that the citation targets a Context Lattice item. It does not describe include_raw, its default, or its effect, so an agent is left to guess how to request the raw variant. This is a significant gap for a two-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 gives a specific action—resolving a single Context Lattice citation—and an additional verification behavior, which separates this from a plain search or sync operation. It does not fully demes multiple beats "Context Lattice" and "original source file" due to jargon, so no full 5.

  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 it is used when you already have a citation to resolve, rather than when searching or syncing. It never explicitly contrasts with siblings or explains when not to use it; the intended spot in a generate pipeline is inferred.

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

• memory_searchA
  3.6/5.0
  Behavior4/5

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

  With no annotations provided, the description bears the full burden and meaningfully warns that results are 'bounded and untrusted' and that the tool returns citations. That adds real behavioral context beyond the name and schema, though it does not explicitly state whether search mutates memory or what boundedness means in operation.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  One compact sentence with no filler. Every phrase earns its place: the resource, the search operation, and the caveats on returned evidence.

  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 output schema exists and the description gives the most important search-relevant caveat: evitable. However, with zero parameter coverage in the schema and no usage routing among siblings, the description is adequate but not complete enough for robust agent understanding.

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

  Parameters1/5

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

  Schema description coverage is 0% and the description never names or explains query, limit, or token_budget. 'Bounded' slightly hints at limits/token caps but does not map to specific parameters, leaving the required query and both optional controls semantically under-explained.

  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 'Search', identifies the resource as 'durable coding-agent memory', and states the return shape as 'bounded, untrusted, cited evidence'. This distinguishes memory_search from siblings such as memory_get or memory_explain, whose names imply other operations.

  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 task context is implied: use it when you need to search memory and retrieve cited evidence. However, it never explicitly contrasts this with memory_get, memory_explain, or other siblings, so the agent is left to infer when one should be preferred over another.

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

• memory_statusA
  4.5/5.0
  Behavior4/5

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

  With no annotations, this description carries the burden of transparency. It explicitly discloses that the tool does not report message content, which is an important behavioral boundary. The verb 'Report' also implies a non-mutating, observability-focused behavior despite no readOnlyHint annotation.

  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, tight sentence with no filler. The key scope ('corpus, schema, index model, and allowed-source health') appears before the clarifying exclusion, making it easy to scan.

  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 that the tool has no parameters and has an output schema, the description provides all needed selection context: what health areas are reported and what is explicitly excluded. There is no missing information that would prevent an agent from invoking it 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 no semantic contribution is required from the description. The schema fully covers the empty parameter set, meeting the baseline for parameterless tools.

  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 ('Report') with a specific resource: corpus, schema, index model, and allowed-source health. The added 'without message content' clause disambiguates it from memory_search and memory_get, which would return content.

  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 context is clear: this is a health/status tool, and the 'without message content' phrasing tells an agent not to use it when message content is needed. It does not explicitly name alternatives or contain a formal when-not-to-use rule, so it is slightly short of a 5.

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