Server Quality Checklist

Tool Scores

• aetre_author_preflight_benchmarkC
  2.9/5.0
  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. Yet it only says the tool 'calculates' metrics — it never discloses what the return value looks like, whether the optional api_key triggers external service calls or lifts rate limits, or whether this is a long-running/heavy computation. For an analysis tool with zero annotation coverage, this is a significant transparency gap.

  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 front-loaded sentence that leads with the primary purpose ('pre-submission diagnostic scorecard') before listing outputs. There is zero waste. It loses one point only because it packs several deliverables into a somewhat dense clause rather than breaking them out.

  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?

  This is a complex tool producing multiple outputs (novelty percentile, disagreement risk, prescriptive actions) with no output schema to fall back on, yet the description never states the return format. An agent cannot predict whether it receives percentages, a report, a score, or structured JSON. For a 4-parameter benchmark tool with no output schema, the description should disclose the deliverable shape.

  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 of 3 applies. The schema already documents all four parameters clearly (text, title, api_key, selection_boundary), including the tau default of 1.2. The description's mention of 'crowd novelty percentile' loosely maps to the selection_boundary concept but adds no parameter-level detail beyond what the schema supplies.

  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-context ('diagnostic scorecard for authors') and enumerates concrete outputs (crowd novelty percentile, reviewer disagreement risk, refinement actions), which distinguishes it from analytical siblings like triage_proposal or simulate_benchmark. It falls short of 5 because the tool's relationship to the 'aetre_preflight' family isn't fully pinned down, but 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?

  The 'pre-submission diagnostic' framing implies a use-case context but provides no explicit when-to-use vs when-not-to guidance and names no alternatives. Among ~20 similar aetre siblings (triage_proposal, batch_triage, calibrate_scorer), an agent is left to infer that this is the one to run before submission, with no exclusions or routing cues.

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

• aetre_batch_triageC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description bears full responsibility for disclosing behavior. It does mention 'disclosed, uncalibrated' indicators and outlines the output streams, but it fails to state whether the operation is read-only, has side effects, or what error conditions might arise. The absence of any description of return formatting or side effects leaves significant 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.

  Conciseness4/5

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

  The description is a single dense sentence with the primary action ('Batch applies...') front-loaded. It efficiently packs three output types and stream names into one clause, with no filler words. It is appropriately sized given the complexity, though it could be slightly clearer with a bulleted structure.

  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 batch tool with no output schema, the description should explicitly state what the agent receives in return. It names computed ranks and streams but does not describe the output structure, pagination, error handling, or any limitations. Given no annotations, the description falls short of what is needed to call the tool confidently.

  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 all three parameters. The description adds minimal meaning beyond the schema, only rephrasing the 'cohort' as proposals and implying the selection boundary without providing syntax or format details. This meets the baseline for high coverage but adds little value.

  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 (batch applies disclosed, uncalibrated lexical indicators) and the resource (a cohort), and lists the specific computational outputs (heuristic ranks, VOI ranks, and stream allocation with named streams). It distinguishes itself from siblings via the 'Batch' prefix, though it does not explicitly contrast with aetre_triage_proposal or other related tools.

  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 such as aetre_triage_proposal or aetre_calculate_voi. The description does not mention conditions, exclusions, or criteria for choosing batch over single-proposal processing, leaving the agent to infer usage purely from the name.

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

• aetre_evaluate_stakingC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description must convey behavioral traits. It says 'Simulates,' implying a non-mutating computation, but it does not explicitly state that it has no side effects, requires an API key (though listed in schema), or what happens if inputs are invalid. It fails to disclose whether it is read-only or if any external data is accessed.

  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 sentence without fluff, delivering the core purpose efficiently. It is appropriately front-loaded with the primary action and context, though it is slightly dense and could be broken into clearer clauses. Overall, it is concise and structured acceptably.

  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 and no annotations, the description leaves critical gaps. It does not describe the result format (e.g., equilibrium number of submitters, threshold conditions), any assumptions or edge cases (e.g., when N < K), or the need for the api_key parameter. An agent cannot fully anticipate the tool's behavior or output from this description alone.

  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 schema description coverage is 100%, so all parameters are already explained (e.g., generation_cost, submission_fee). The description adds only contextual phrasing like 'generative AI generation costs' and 'refundable submission deposits,' which map directly to those parameters without adding new semantic detail beyond the schema. This meets the baseline for high coverage with no extra compensation needed.

  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 ('Simulates') and object ('submitter entry equilibrium') with context (generative AI generation costs, refundable submission deposits). It is clear on what the tool does, but it does not explicitly distinguish itself from sibling simulation tools like aetre_quadratic_staking or aetre_heterogeneous_queues, which may also model related equilibria.

  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 explicit guidance on when to use this tool versus alternatives. It does not mention conditions like 'use when modeling spam floods with deposits' or compare to siblings such as aetre_quadratic_staking. The only cue is implied from the tool name and description, leaving the agent to infer its appropriate use.

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

• aetre_heldout_backtestC
  2.9/5.0
  Behavior2/5

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

  No annotations are present, so the description carries the full disclosure burden. It mentions 'runs a backtest' and 'evaluating', but does not indicate whether the operation is read-only, whether it requires specific datasets or permissions, what side effects (if any) exist, or what the output structure is. For a computation tool this is a notable gap.

  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?

  One sentence, efficiently packs the action and evaluation scope. It is front-loaded with the core purpose, though the long list of metrics makes it slightly dense. Still, it is appropriately concise with no filler.

  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 complex (8 policies, multiple metrics, statistical intervals) but the description provides no details on how to interpret results, what 'true decision flips' means, or what the output looks like. With no output schema and no annotations, this is insufficient for an agent to use it correctly without further context.

  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%, with each parameter described in the input schema. The description itself adds no extra semantic value beyond the schema—it doesn't clarify parameter relationships or provide examples. Baseline 3 is appropriate because the schema already documents parameters.

  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 ('Runs') and a clear resource ('multi-policy held-out review allocation backtest'), and names the key evaluation targets (decision flips, precision, recall, bootstrap intervals). It is not a tautology and conveys a concrete action, though it does not explicitly differentiate from sibling tools with similar backtesting purposes.

  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 choose this tool over siblings like aetre_batch_triage or aetre_simulate_benchmark. The description implies a backtest use case but does not state context, prerequisites, or exclusions.

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

• aetre_multi_attribute_voiC
  2.9/5.0
  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 states the tool computes and outputs, but does not describe any side effects, limitations, assumptions (e.g., orthogonality as a requirement), error conditions, or the structure of the returned data. The behavior is essentially self-evident from the name and schema, adding little beyond the obvious.

  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, dense sentence that front-loads the core functionality ('Computes multi-attribute Bayesian VOI') and then explains the context and outputs. It contains no redundancy or filler. It is slightly long but remains efficient and well-structured.

  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 has multiple parameters, a nested array, and no output schema. The description mentions the output shape conceptually (composite VOI and optimal review targets) but does not specify the return format, pagination, or any behavioral nuances. Given the complexity of the tool, the description is adequate but leaves gaps around output details and usage context.

  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 context by listing example dimension names (Novelty, Rigor, Impact, Feasibility) and the property 'orthogonal', which hints at independence between dimensions. However, it does not elaborate on the other parameters (composite_threshold, review_cost_per_dim) beyond what the schema provides. The added meaning is marginal.

  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 verb 'Computes' and the resource 'multi-attribute Bayesian Value of Information', with specific context about dimensions (Novelty, Rigor, Impact, Feasibility). It also mentions the output (composite VOI and optimal dimension-specific review targets). It does not explicitly name a sibling, but the 'multi-attribute' and 'orthogonal' wording differentiates it from likely single-attribute variants like aetre_calculate_voi.

  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 on when to use this tool as opposed to alternatives. It does not mention when this should be preferred over aetre_calculate_voi, aetre_correlated_posterior_update, or aetre_heavy_tailed_voi, nor does it state any conditions or exclusions. The description is purely functional.

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

• aetre_sequential_stopping_ruleC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full disclosure burden, yet it discloses little beyond the action itself. It does not state the return format (what the boundaries look like), error or edge-case behavior (e.g., empty reviews array), or any numerical caveats. The read-only nature is only implied by the non-mutating verb 'Calculates', which is the sole behavioral signal.

  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 sentence of roughly twenty words with zero redundancy. The primary action is front-loaded ('Calculates optimal dynamic Bayesian stopping boundaries'), followed by the decision outcomes and the driving mechanism. Nothing in the description is wasted, packing the core semantics into minimal length.

  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 fairly complex statistical tool with 8 parameters, no output schema, and no annotations, the description is thin. It omits the return structure of the boundaries, usage context, and the relationship between the optional cost/confidence/noise parameters and the stopping decision. The schema covers parameter meanings, but the operational context an agent needs to call this correctly is under-specified.

  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 all 8 parameters (prior_mean, prior_variance, threshold, reviews, next_review_cost, confidence_threshold, next_review_noise_sd) with examples. The description adds only the conceptual tie-in of 'posterior decision confidence and boundary VOI' as the basis, which lightly frames confidence_threshold but does not materially extend the schema. The coverage-based baseline of 3 holds.

  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 ('Calculates') with a specific resource ('optimal dynamic Bayesian stopping boundaries for sequential reviews'), enumerates the three decision outcomes (Accept, Reject, Solicit More Reviews), and names the mechanism (posterior confidence and boundary VOI). It is topic-distinct from the VOI siblings (aetre_calculate_voi, aetre_heavy_tailed_voi), so an agent can broadly tell it apart, though no sibling is explicitly named.

  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 on when to use this tool versus the many related VOI or posterior-tool siblings (e.g., aetre_calculate_voi, aetre_heavy_tailed_voi, aetre_triage_proposal). There are no conditions stated for when its stopping-boundary logic is appropriate, nor any exclusions or alternative routing. Usage must be inferred from the purpose phrasing alone.

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

• aetre_simulate_benchmarkC
  2.9/5.0
  Behavior2/5

  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 mentions that the tool computes intervals and clarifies they are run-to-run rather than confidence intervals, which is a positive nuance. However, it fails to disclose whether the tool has side effects (e.g., mutates state), what authentication is required beyond the api_key parameter, or any rate or resource limits. The lack of output description 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.

  Conciseness4/5

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

  The description is a single, dense sentence that front-loads the core action and then specifies metrics and statistical detail. There is no redundant or filler text. While it is information-dense, it is not overly long and every clause adds meaning, earning a solid 4.

  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 the tool's complexity (8 parameters, Monte Carlo simulation) and the absence of an output schema and annotations, the description should explain what the tool returns. It does not mention the result format, whether it is a table, a summary, or a detailed breakdown. It also does not discuss any prerequisites or consequential requirements beyond the api_key parameter. This is a major omission for an agent to use the tool effectively.

  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% per the context, so all 8 parameters have descriptive schema entries (e.g., 'Number of Monte Carlo simulation replicates (default: 50)'). The description does not add any parameter-specific details beyond what the schema already provides; it only references the simulation design generally. Thus it stays at the baseline of 3.

  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 verb ('Runs') on a defined resource ('paired-cohort Monte Carlo simulation') and enumerates the exact metrics compared (Quality Throughput, FDR, Unconventional Recall, Human Reviews) across all 4 screening regimes. It also adds a precision detail about the intervals, which distinguishes it from generic simulation descriptions. It does not explicitly name a sibling tool, but the specificity is strong enough to convey distinct purpose.

  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 the many sibling tools such as aetre_heterogeneous_queues or aetre_author_preflight_benchmark. The description does not mention any exclusions, prerequisites, or alternative conditions. The agent must infer the intended use case from the name and description alone, which is insufficient for such a specialized simulation tool.

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

• aetre_heterogeneous_queuesB
  3.2/5.0
  Behavior2/5

  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, but it only says 'evaluates' and 'generating actions' without clarifying whether it mutates state, requires any special permissions, or is purely analytical. This is a significant gap for a tool that appears to be a simulation/analysis utility.

  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 that efficiently captures the core purpose and expected outputs. There is no wordiness, and every phrase contributes to the agent's understanding of the tool's function.

  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 description lacks crucial details: there is no mention of what the output looks like, the necessity of the api_key, the meaning of 'bottleneck domains' or 'capacity rebalancing actions', or how the network is modeled. For a tool with no output schema, the description is too thin to fully guide an agent.

  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% for the top-level fields (pools and api_key), and the description adds no extra meaning about how parameters like arrival_rate or service_rate relate to the evaluation. The baseline of 3 is appropriate since the schema documents the parameters adequately, though the description could have added context on their role in bottleneck identification.

  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 evaluates a multi-specialist heterogeneous reviewer network, identifies bottleneck domains, and generates capacity rebalancing actions. It gives a specific verb ('Evaluates'), a resource ('multi-specialist heterogeneous reviewer network'), and concrete outputs, making it distinct from siblings like aetre_congestion_matching or aetre_system_catalog.

  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 on when to use this tool versus alternatives. It does not state any conditions, prerequisites, or alternatives, leaving the agent to infer usage from the name and description alone.

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

• aetre_proposition_1_boundB
  3.2/5.0
  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. It signals a pure read/compute operation ('Calculates... to determine if') with no mutation, which is reasonably transparent. But it omits the return format, whether a result of 1 vs a fractional bound means the capacity constraint binds, any error conditions, and when the optional api_key is actually needed — gaps that are more consequential because no annotations cover them.

  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 dense sentence with no filler; verb and purpose are front-loaded. The parenthetical formula uses undefined symbols, which slightly hampers readability, but overall it is efficient and 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?

  For a mathematical tool with no output schema, the description is the only place to describe the result, yet it does not state what the tool returns (a boolean capacity flag, the numeric ceiling R_N, or both) nor how the inputs translate into the derived H_N. The intent is clear enough, but an agent is left guessing at the output contract.

  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 all four parameters (p_H with example 0.067, N, K). The description's formula adds the symbolic context of K_N and H_N but never maps parameters to variables, notably H_N, which must be derived as total_candidates × high_value_rate. This leaves the formula-to-parameter relationship implied rather than explicit, a modest added value on top of a complete 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?

  States a specific verb ('calculates') and resource ('Proposition 1 theoretical recall ceiling') plus the governing formula R_N <= min(1, K_N / H_N), making the core purpose clear. The 'determine if a pipeline is mathematically capacity-constrained' framing adds purpose context. However, it does not differentiate from numerically close siblings like aetre_recall_scaling_curve, so an agent has no basis to pick this over that.

  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 on when to use this tool versus alternatives. The phrase 'theoretical recall ceiling' implies this is the analytical/closed-form bound versus presumably empirical siblings (aetre_simulate_benchmark, aetre_heldout_backtest), but this distinction is only implied, never stated. No exclusions, no conditions, and no named alternatives are provided.

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

• aetre_heavy_tailed_voiB
  3.3/5.0
  Behavior2/5

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

  No annotations are present, so the description must disclose behavior. It only states that it 'Calculates' something; it does not disclose whether it is a pure function, any assumptions about the Pareto tail, the nature of the result (e.g., a numeric VOI score), error conditions, or computational cost. The description adds minimal behavioral context beyond the formula name.

  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 sentence that is concise and front-loads the core purpose. There is no redundant information, and it reads efficiently. Slightly more might be warranted for a complex tool, but it is not bloated.

  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 specialized and complex (7 parameters, no output schema, heavy-tailed VOI concept) yet the description does not explain the return format, assumptions, or when to use it relative to similar sibling tools. Without annotations or an output schema, the agent lacks essential context about the result and invocation scenario. The schema covers parameter names but not the overall behavior or expected output.

  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 all parameters already have documented meanings (e.g., posterior_mean, variance, tail_index_alpha). The description adds no additional parameter-level detail or guidance on how to set these values; it merely restates the general purpose. Baseline 3 applies as the schema does the heavy lifting.

  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 specific verb 'Calculates' and names the resource 'Generalized Pareto / Heavy-Tailed VOI', and states its purpose ('optimize selection pipelines for positive black swan breakthrough discovery') which clearly differentiates it from sibling tools like aetre_calculate_voi and aetre_multi_attribute_voi. No confusion about what it does.

  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 a usage context (positive black swan breakthrough discovery) but does not explicitly say when to choose this tool over the many other VOI-related siblings. There is no mention of alternatives, conditions, or scenarios where this tool is preferred, leaving the agent to infer based on the term 'heavy-tailed'.

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

• aetre_triage_proposalB
  3.3/5.0
  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. It does disclose that the indicators are 'transparent, uncalibrated' and that the output is 'not a validated estimate of scientific quality', which addresses reliability. However, it omits other behavioral traits like whether the operation is read-only, error behavior, or performance implications. It's a modest disclosure but leaves 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 two sentences with no wasted words. The core action and outputs are front-loaded, and the caveat about not being a validated estimate is appended directly. This is efficient and 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?

  For a tool with no output schema and no annotations, the description gives a reasonable overview but lacks important context. It lists the three stage routes but doesn't explain what they mean or how an agent should interpret them. The tool appears moderately complex, and the description doesn't clarify expected return structure or edge cases, making it only partially complete.

  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?

  With 100% schema description coverage, the schema already documents all four parameters. The description references the algorithm's nature but does not add specifics about parameter syntax or semantics beyond the schema. The baseline of 3 is appropriate given that the schema carries the descriptive load and the description adds limited extra meaning.

  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 applies lexical routing indicators and calculates a VOI index plus a stage route, with specific verbs and resource. It also includes a caveat distinguishing it from validated quality estimates, which helps set it apart from similar tools like aetre_calculate_voi. However, it doesn't explicitly name sibling alternatives, so it stops short of full differentiation.

  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 does not mention any conditions, exclusions, or why an agent should choose this over aetre_calculate_voi or aetre_batch_triage. An agent must infer the intended use case from the tool name and vague 'triage' concept.

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

• aetre_exploration_auditB
  3.4/5.0
  Behavior2/5

  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 discloses that it calculates an estimator and confidence intervals, but it does not state whether the operation is read-only, any side effects, or the output format. It also fails to mention the required api_key parameter, leaving the agent unclear about access requirements. This is a notable gap for a tool with no annotation support.

  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 sentence that efficiently conveys the core computation and purpose, front-loading the main action. The technical terminology (e.g., Horvitz-Thompson estimator) is specific but may require domain knowledge, yet the structure is clean and waste-free.

  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 tool is a statistical calculation with three required numeric inputs and no output schema, the description should at least state what the function returns (e.g., the estimate and confidence interval). It does not, nor does it mention the api_key field. While the purpose is clear, the lack of output details and access requirements makes it only minimally complete.

  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 input schema provides complete descriptions for all four parameters (deprioritized_pool_size, audited_sample_size, audited_high_value_found, and api_key), so the schema already covers parameter semantics. The description adds no additional guidance about parameter relationships or constraints, so it is at the baseline for high 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 a specific action ('Calculates'), a specific resource ('unbiased Horvitz-Thompson exploration audit estimator (H_hat_D)'), and the purpose ('to catch false negative breakthroughs'). It distinguishes this tool from sibling tools like aetre_calculate_voi by focusing on auditing deprioritized candidates, which is a unique function.

  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 when to use the tool (when auditing deprioritized candidates), but it does not explicitly state conditions, alternatives, or exclusions. There is no mention of prerequisites like the api_key or when not to use it, so usage guidance is only implied by the purpose.

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

• aetre_system_catalogB
  3.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description bears the full burden of behavioral disclosure. It states that the tool 'returns' metadata but does not mention side effects, read-only nature, authentication requirements, rate limits, or error behaviors. The optional api_key parameter hints at tier verification but the description does not explain when it is needed. For an introspection tool, read-only status is likely but unstated, and the description fails to clarify any behavioral nuances beyond the basic return.

  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, information-dense sentence that front-loads the core purpose ('comprehensive system introspection') and enumerates the specific content areas. It is appropriately sized for the tool's complexity and contains no unnecessary words. The structure is efficient, though it could benefit from breaking out the categories for readability; still, it earns points for efficiency.

  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 tool has no output schema and no annotations, the description should ideally explain what 'returning' entails in terms of structure or usage. It does not specify the return format, pagination, or how the query_type parameter shapes the output beyond the schema's enum. It also does not mention that query_type defaults to 'all' (schema provides that). The description is adequate for a simple catalog tool but leaves room for an agent to wonder about output structure and edge cases.

  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 fully documents both parameters (api_key and query_type with its enum). The description adds high-level category names that roughly map to enum values (e.g., 'mathematical tools' -> 'tools', 'institutional tiers' -> 'institutional_tiers'), but it does not explicitly tie the listed categories to specific query_type values. This adds marginal semantic context beyond the schema but does not fully compensate for the schema's already thorough documentation.

  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 purpose: comprehensive system introspection returning specific categories of AETRE metadata (architecture, fixtures, adapters, connectors, tools, tiers). This verb+resource combination distinguishes it from sibling tools, which are all specific computational functions (e.g., aetre_calculate_voi, aetre_triage_proposal). An agent can immediately recognize this as a catalog/inventory tool, not an operation.

  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 does not explicitly state when to use this tool versus alternatives. It is evident from the name and description that this is for introspection, but there is no explicit guidance like 'use this to discover available capabilities' or 'for a specific calculation, use one of the aetre_* function tools'. The usage context is implied rather than spelled out, leaving the agent to infer that this is a discovery tool.

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

• aetre_recall_scaling_curveA
  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 must carry full behavioral burden. It discloses only the calculation action and does not state read-only nature, absence of side effects, or expected output format. For a theoretical tool, this leaves uncertainty about side effects and return type.

  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 core action and resource, includes illustrative multipliers, and has zero extraneous content. Efficient and to the point.

  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 tool with no output schema, the description should clarify the return value or data format; it does not. It also omits any mention of prerequisites or typical use case scenarios, leaving agents to infer what the curve output looks like. The core purpose is clear, but surrounding 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 covers all 5 parameters at 100%, so baseline is 3. The description reinforces the 'multipliers' parameter with example values and adds the concept of 'capacity collapse points' but does not provide additional syntax or semantics beyond the schema. Adequate but not enhanced.

  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?

  States a specific verb 'Calculates' with a precise resource 'Proposition 1 theoretical recall decay curve' and scope 'across arrival expansion scales'. Clearly differentiates from sibling aetre_proposition_1_bound by focusing on the curve and capacity collapse.

  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?

  Implied usage: to analyze recall decay under scaling, but no explicit statement on when to choose this over alternatives like aetre_proposition_1_bound or aetre_system_catalog. Lacks any 'when not to use' guidance.

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

• aetre_calculate_voiA
  3.6/5.0
  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 states the tool performs a calculation, which suggests a read-only operation, but it omits any mention of the api_key parameter and whether this triggers an external service call. No side effects, failure modes, or prerequisites (e.g., valid variance) are disclosed. The description is adequate for a pure computation but leaves the API dependency unexplained.

  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 filler. The verb, object, and context appear in the correct order, and every word contributes to the meaning. It is an ideal length for communicating the core function.

  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?

  This is a complex Bayesian VOI calculator with no output schema and no annotations. The description does not explain what the tool returns (a single value? a decision?), how to interpret the result, or any caveats about input validity. An agent cannot infer the expected output or which parameter combinations are meaningful, making the definition incomplete for practical 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?

  Schema description coverage is 100%, so the baseline is 3. The description adds no parameter-specific detail; it only restates the high-level purpose. All parameter meaning is already in the schema, so the description does not contribute additional value beyond what the schema provides.

  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 a specific verb ('Calculates'), a precise object ('exact Bayesian Value of Information'), and a narrowing context ('crossing a top-K selection boundary under Gaussian conjugate updates'). This distinguishes it from sibling tools like aetre_heavy_tailed_voi and aetre_multi_attribute_voi, which address different distributional or structural assumptions.

  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 when to use this tool by specifying the Gaussian conjugate setting, but it does not explicitly name alternatives or say 'use this instead of heavy_tailed when...'. There is no guidance on when not to use it, nor does it mention a fallback. The applicability is tacit rather than spelled out.

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

• aetre_calibrate_scorerA
  3.6/5.0
  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 behavioral disclosure. It transparently reveals the operation (fit a scaling model) and the precise return values, but it does not address side effects, whether this is a read-only analytics computation, or any execution cost relative to the optimization iterations it accepts.

  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 conveys the action, inputs, algorithm, and all four outputs without wasted words. Every element earns its place, and the most discriminant detail (Platt logistic scaling) leads the sentence.

  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 fit-and-return tool, the description is nearly complete: it covers the algorithm, the expected inputs, and the four return values, which partially substitutes for the missing output schema. The only gap is the absence of usage guidance against sibling calibration and benchmarking tools.

  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 every parameter (required scores/labels, optional api_key, iterations, learning_rate). The description only re-states that scores are continuous and labels are binary, adding little meaning beyond the schema's own wording. Baseline 3 applies.

  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 verb ('fits'), a well-defined resource (Platt logistic scaling on continuous scores and binary labels), and enumerates the outputs (slope, intercept, ECE, Brier score). The calibration focus and named algorithm set it apart from the sibling tools, which cover VOI, staking, queues, and triage.

  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. None of the siblings (e.g., aetre_recall_scaling_curve, aetre_heldout_backtest) are referenced, and no exclusions or selection criteria are given. An agent must infer calibration context on its own.

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

• aetre_correlated_posterior_updateA
  3.6/5.0
  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 states the tool calculates a posterior and prevents overconfidence, which are beneficial outcomes, but does not disclose whether the operation is read-only, any side effects, or specific requirements beyond the API key mention. The 'Enterprise license key required' phrase is somewhat contradicted by the schema (api_key is not in required list), but this is a schema-description mismatch, not an annotation contradiction. No further behavioral detail is given.

  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, focused sentence that leads with the primary action and purpose. It avoids redundant phrasing and front-loads the key concept. It is concise without being under-specified, though it could include a bit more usage context without becoming verbose.

  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 core purpose and mentions the key differentiator (correlated noise) but lacks guidance on the expected output format (e.g., does it return a tuple of mean and variance?) and does not specify any prerequisites besides the API key. Given there is no output schema, the description should at least hint at the return shape. It also does not provide usage scenarios or caveats. For a complex Bayesian tool, more detail would be helpful.

  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 schema has 100% description coverage, so all parameters already have descriptions. The tool description adds contextual meaning (correlation, overconfidence) but does not deepen the meaning of individual parameters like prior_mean or prior_variance beyond what the schema already states. For example, it does not explain how inter_agent_correlation is used in the calculation beyond what the schema already says. Baseline 3 is appropriate given the high 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 a specific action ('Calculates') on a specific resource ('Bayesian posterior mean and uncertainty'), with a distinctive qualifier ('under correlated multi-agent evaluator noise'). It also mentions the purpose ('preventing artificial overconfidence from redundant LLM outputs'), which differentiates it from sibling tools focused on queues, VOI, staking, etc. The verb and resource are unambiguous.

  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 when to use the tool (when you need posterior updates with correlated noise) but does not explicitly state when not to use it or point to any alternative sibling. It does not mention conditions like 'use aetre_calculate_voi for value of information' or any exclusion criteria. The guidance is only implicit through the problem statement.

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

• aetre_quadratic_stakingA
  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 does not disclose any behavioral aspects such as read-only status, authentication requirements (despite the api_key parameter), rate limits, or side effects. The description only explains the calculation formula without addressing safety or access constraints.

  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, well-structured sentence that front-loads the verb 'Calculates', includes the precise formula, and states the purpose. It has no unnecessary words and is appropriately sized.

  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?

  Despite the clear formula and purpose, the description lacks information about the return value/output format (with no output schema), error behavior, or the requirement for api_key. Given the tool's complexity and absence of annotations, more context about expected outputs and usage constraints would be needed for complete understanding.

  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 each parameter is individually described. The description adds the formula Stake(m)=S_0*m^gamma, which clarifies the relationship among base_fee, submission_count, and escalation_exponent, going beyond individual parameter descriptions and providing cohesive semantic context.

  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 calculates super-linear anti-sybil staking deposit requirements, specifies the formula Stake(m) = S_0 * m^gamma, and gives the intended purpose (deterring AI spam while preserving human entry). It distinguishes itself from siblings like aetre_evaluate_staking by focusing on calculation, not evaluation.

  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 when deposit requirements need to be computed for anti-sybil purposes, but it does not explicitly state when not to use it or compare to alternatives. No exclusions or alternative routing are provided.

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

• aetre_check_governorA
  3.9/5.0
  Behavior2/5

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

  With no annotations provided, the description must carry the full burden of behavioral disclosure. It states it returns recommendations, implying it does not apply them, but it does not explicitly state whether the call is read-only, has side effects, or requires any special handling beyond the API key mentioned in the schema. This lack of explicit behavioral disclosure is a gap, though not contradictory.

  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, well-structured sentence that front-loads the purpose and includes the key condition. No extraneous words, and the information density is high.

  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 explains the purpose and condition, but with no output schema, it does not specify the structure or details of the 'governor throttle recommendations' it returns. For a tool with six parameters and no operation annotations, an agent would benefit from knowing the output shape or any side effects. This is a notable gap.

  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 parameters are already documented. The description adds value by contextualizing them: it explains that the tool uses Kingman's Heavy-Traffic approximation and that recommendations are triggered when utilization exceeds 0.85, which clarifies the role of the rate parameters and the threshold. This goes beyond simple schema descriptions.

  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 what the tool does: it evaluates evaluator queue load using a specific mathematical approximation (Kingman's) and returns throttle recommendations based on a utilization threshold. This is specific and distinguishes it from sibling tools that handle different queue or evaluation concerns.

  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 a clear condition for use: when utilization exceeds rho >= 0.85. It implies when to call this tool, but it does not explicitly mention alternatives or when not to use it, though the context is sufficient for most agents.

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

• aetre_congestion_matchingA
  3.9/5.0
  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, and it does disclose real behavioral content: the optimization enforces a hard per-reviewer utilization cap of rho <= 0.85 and prioritizes affinity. However, it does not state what happens when the constraint set is infeasible, whether the result is a recommendation or a state change, or what the tool 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 zero filler: the main action leads, followed by the objective and the constraint. 'Kingman queue utilization constraints (rho <= 0.85)' is dense but precise, and every clause 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?

  The description nails the 'what' and 'why' but leaves output semantics unaddressed — there is no output schema and the description never hints at what the tool returns (e.g., an assignment plan, score matrix, or feasibility report). Given the algorithmic complexity and constraint-enforcement behavior, infeasibility handling is also a gap.

  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, but the description adds value by tying parameters to the algorithm: domain/keyword affinity maps to proposal.domain/keywords and reviewer.domain/expertise_tags, and the rho <= 0.85 constraint operationalizes target_utilization. This semantic glue helps an agent understand why each parameter matters beyond its type and schema text.

  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 opens with a precise verb-resource pair — 'Optimizes reviewer-to-proposal assignment' — and immediately specifies the dual objective: maximize domain/keyword affinity and enforce Kingman queue constraints (rho <= 0.85). This specificity makes the tool unmistakable among siblings like aetre_heterogeneous_queues and aetre_batch_triage.

  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?

  No explicit when-to-use or when-not-to-use guidance is given, and no alternative tools are named. The intended scenario (matching reviewers to proposals under workload caps) is only implied by the objective described, so an agent must infer applicability rather than being told.

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