Server Quality Checklist

Tool Scores

• livingstack.session_closeB
  3.2/5.0
  Behavior3/5

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

  Annotations already signal a non-read-only, non-idempotent mutation. The description adds useful context by saying the local ledger is preserved, which clarifies that closing finalizes state without destroying evidence, but it does not disclose what happens on repeated closure or whether the session becomes immutable.

  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?

  A single 12-word sentence that is front-loaded with the action and consequence. It loses one point for the typographical issue (tamper-evident rendered as tamper-evident) and for not adding any word on return behavior.

  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 two-parameter tool with an output schema, the description covers the core purpose adequately. It does not explain what happens to an already-closed session, whether the caller receives the ledger, or what the 'reason' influences, which an agent might need when invoking the tool.

  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 bouth parameters are already documented. The description adds no extra meaning about valid reason values or the effect of the default 'completed', but the high schema coverage means the baseline of 3 applies.

  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 ('Close') and a clear resource ('proof session'), and adds a meaningful consequence (preserving the tamper-evident local ledger). It distinguishes itself from an abandon or cancel action, though it does not explicitly differentiate from a potential sibling like 'session_end'.

  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 explains when to call this tool versus any alternative, and no exclusions or prerequisities are stated. Since the sibling list is empty, the description misses the chance to say whether closing is the final step in a proof workflow or what distinguishes it from other session operations.

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

• livingstack.session_statusB
  3.2/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds context about the scope of what gets verified (lifecycle, budget, counts, ledger head) but no further behavioral traits such as error conditions or side effects, which is acceptable given the annotation coverage.

  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?

  A single, efficient sentence with no filler; the verb and the four scoped aspects are packed into one clause. It is concise and front-loaded, though it lacks any structural cues for sibling selection.

  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 one-parameter, read-only tool with an output schema and safety annotations, the description is mostly adequate. The main gap is the unmet need to clarify when this tool should be chosen over overlapping siblings like livingstack.status and check_claim.

  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% with session_id documented as 'Session identifier,' so the schema fully handles parameter semantics. The description adds no additional meaning about session_id, matching the baseline for high schema coverage.

  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 the specific verb 'Verify' with the resource 'a session' and names concrete aspects (lifecycle, budget, counts, ledger head), making the tool's function clear and distinct from a tautology. It does not explicitly differentiate from sibling tools like livingstack.status or check_claim, but the listed scope provides enough specificity.

  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; siblings include livingstack.status and check_claim, which could plausibly overlap, yet none are mentioned or contrasted. Usage is only implied by the verb 'Verify' and the listed items, providing no explicit context or exclusions.

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

• livingstack.statusA
  3.5/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description's 'Inspect' aligns with that safety profile. It adds useful context by identifying what is inspected, but it does not describe response behavior or edge cases; with strong annotations present, a 3 is appropriate.

  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 short sentence that front-loads the action and object. It contains no filler, no repeated schema information, and every word earns its place.

  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 no parameters, read-only and idempotent annotations, and an available output schema, the description is sufficient for a simple status-inspection tool. The phrase 'paid boundary' is mildly domain-specific, but the output schema presumably clarifies the return contract, so nothing critical 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?

  There are zero parameters and schema description coverage is 100%, so there is nothing for the description to add. The zero-parameter baseline of 4 applies here.

  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 imperative verb, 'Inspect,' and names a concrete resource: 'Community capabilities and the paid boundary.' This is clear, but it does not explicitly differentiate the tool from the sibling livingstack.session_status, leaving the agent to infer the distinction from the resource noun.

  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 alternatives such as session_status or check_claim. The imperative 'Inspect' implies a read-only status check, but there is no explicit context, exclusions, or alternative routing.

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

• livingstack.record_outcomeA
  3.6/5.0
  Behavior4/5

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

  The description adds useful behavioral context beyond the annotations: it explicitly states the operation consumes one authorization, implying single-use and a state-changing effect. It also conveys that the result is transformed into 'typed evidence,' which is not captured by the annotation flags.

  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 terse sentence with no filler and front-loads the key behavior ('Consume'). It is concise and memorable, though slightly abstract phrasing like 'bind its observed result to typed evidence' sacrifices some plain-language clarity.

  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 output schema and high parameter schema coverage, the description does not need to explain return values or every parameter. However, it lacks guidance on the expected lifecycle context, such as requiring a prior authorization or that the authorization becomes invalid after recording. The core behavior is present, but the surrounding operational context is incomplete.

  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 83%, so the schema already documents most parameter meanings. The description ties the idea of 'typed evidence' to the evidence parameter but does not add meaning beyond the schema. A baseline score of 3 is appropriate because the description does not need to compensate.

  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 ('Consume') and resource ('one authorization'), and clearly indicates the action is recording an observed result as evidence. It is clear enough to distinguish this from the sibling tools, though it does not explicitly name or contrast any sibling.

  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 'Consume one authorization and bind its observed result' implies this should be used after an authorization has been acted on and its outcome is known. However, there is no explicit guidance about when to use this tool instead of related tools like check_claim or session_close, and no stated prerequisites or exclusions.

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

• livingstack.authorize_actionA
  3.7/5.0
  Behavior3/5

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

  Annotations are all false, so the description carries the full burden. It clearly discloses a key behavioral guarantee: the tool never executes the action. However, it does not mention potential side effects such as budget reservation, record creation, or rejection behavior.

  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?

  Single sentence, no filler, and the most important distinction ('never executes it') is front-loaded. Every word earns its place.

  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?

  With six parameters, an output schema, and full schema coverage, the minimal description is mostly adequate. It lacks workflow ordering (e.g., after session_start) and side-effect details, but the core never-executes guarantee and complete schema keep it at minimum viable.

  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 conceptual grouping ('scope risk and budget') that maps loosely to risk and estimated_cost_usd, but provides no parameter-specific details beyond what the schema already documents.

  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 ('gate') and resource ('one local host action'), and immediately distinguishes the tool by stating it never executes the action. This separates it from any execution/effect tool and aligns with its name.

  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 a pre-execution authorization step ('Gate... never executes it'), which gives useful context. However, it does not explicitly state when to call it relative to session lifecycle tools like session_start, nor name alternatives like check_claim.

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

• livingstack.check_claimA
  3.9/5.0
  Behavior3/5

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

  The description adds meaningful behavioral context by constraining evidence to explicitly selected, fresh, successful, and subject-bound items. However, with all annotation hints false, it does not clarify whether the check itself mutates state, requires authorization, or has side effects, leaving some behavioral 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 entire description is one front-loaded, 12-word sentence with no filler or redundancy. Every phrase carries semantic weight and maps to tool behavior.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  An output schema exists, so return-value documentation is not required, but the description omits practical context such as prerequisites (e.g., an active session or previously recorded outcomes) and does not explain how the evidence set is assembled. It is adequate but lean for a tool with six parameters and sibling lifecycle tools.

  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 compresses key parameter semantics: 'explicitly selected' maps to outcome_ids, 'fresh' to max_age_seconds, and 'subject-bound' to subject. Schema coverage is only 67%, so this added mapping is valuable, though required_evidence_types remains 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 states a specific action ('Check a proposed claim') and a specific resource/evidence set ('explicitly selected, fresh, successful, subject-bound evidence'). This clearly separates it from the lifecycle/status/recording siblings, so an agent can identify when this tool is relevant.

  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 context is implied rather than stated: the agent should call this when it has a proposed claim and selected evidence to verify it against. There is no explicit when-to-use or when-not-to-use guidance, nor any mention of sibling alternatives such as record_outcome, so it falls short of explicit routing.

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

• livingstack.session_startA
  4.2/5.0
  Behavior4/5

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

  Annotations only supply readOnly=false, idempotentHint=false, and destructiveHint=false. The description adds valuable behavioral context by disclosing that the session is isolated and that scope and budget are immutable, which are meaningful guarantees beyond the structured annotations. It does not contradict any 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?

  The description is a single front-loaded sentence with no redundant words. It states the core action and the most important constraints without padding.

  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 presence of an output schema, detailed parametter descriptions, and annotations, the description is largely complete for starting a session. It conveys the essential isolated and immutable nature of the session, though it could have briefly mentioned retention or cost behavior to fully round out the context.

  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 100%, so the baseline is 3. The description adds extra semantic meaning by stating that scope and budget are immutable, which clarifies the behavior of the scope and budget_limit_usd parameters beyond their schema descriptions. It does not explain every parameter, but the schema already covers them.

  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 "Start" and a clear resource "isolated proof session," with distinctive qualifiers "immutable scope and budget." It is immediately distinguishable from sibling tools like session_close, status, and check_claim, which perform different lifecycle or inspection actions.

  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 should be used when a new isolated proof session is needed, but it does not explicitly state when to prefer it over alternatives or mention exclusions. It is not misleading, just minimally guiding.

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