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

With no annotations, the description carries the full burden. It discloses the bisection method and the return values (required input, change from baseline, achieved metric, residual), which are useful behavioral traits. It does not mention potential failure modes (e.g., no solution exists) or state effects, but for a read-only solver this is adequate.

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

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

A single, front-loaded sentence states the purpose, method, and return values without waste. It is well-structured and every clause adds meaningful information.

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

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

With no output schema, the description does list the key return values, which is helpful. However, with 8 parameters and no explicit parameter explanations or success/failure conditions, the description is not fully complete for an agent to invoke the tool without additional inference.

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

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

Schema description coverage is only 38% (descriptions exist for inputs, horizon, template, but not for bounds, solve_for, target_value, period_label, target_metric). The description does not compensate: it only indirectly hints at solve_for and target_value via the purpose sentence, leaving bounds, inputs, and period_label unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Solve for') with a clear resource ('input value') and goal ('make an output metric reach a target value'), which distinguishes it from sibling tools like sensitivity_analysis and run_scenario. The mention of 'bisection' further clarifies the numeric method. This is a clear, distinct purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The usage context is implied by the purpose: use this tool when you need to find the input value that achieves a target output metric. However, there is no explicit guidance on when not to use it or how it compares to alternatives like run_scenario or sensitivity_analysis.

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

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

No annotations are provided, so the description carries full burden. It discloses key behaviors: first scenario as baseline, side-by-side comparison with deltas, and optional ranking via compare_metric/goal. However, it does not mention whether the tool has side effects (e.g., executing runs) or what happens with different numbers of scenarios, 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.

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

The description is a single, front-loaded sentence that efficiently communicates the core action and options without redundant words. Every clause adds value: 'Run 2-3 scenarios', 'compare key_results side by side with deltas', 'baseline', and optional ranking.

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

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

There is no output schema and no annotations, so the description must explain both inputs and outputs. It partially explains outputs (key_results, deltas) but omits details on horizon, include_projections, and the required structure of scenarios. For a tool with 5 parameters and no additional schema context, the description is incomplete.

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

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

Schema description coverage is 0%, so the description must compensate. It adds semantic context for compare_metric and goal (ranking), and implies scenarios holds the scenario list. However, horizon and include_projections are completely unexplained, and the structure of scenario objects is not addressed. With 5 parameters and only 2 partially clarified, the description does not sufficiently compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses specific verbs (run, compare) and clearly states the resource (scenarios) and output (key_results side by side with deltas). It distinguishes from siblings like run_scenario by explicitly addressing 2-3 scenarios and comparison, and from sensitivity_analysis by focusing on comparison rather than sensitivity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies usage when comparing multiple scenarios (2-3) and mentions baseline/deltas, but it does not explicitly state when to use this tool over siblings or include exclusions. There is no alternative named, leaving the guidance at an implied level rather than explicit.

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

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 reveals the categories of information returned (health, version, capabilities) but does not state side effects (if any), response format, or whether the check is read-only. This is a sparse disclosure for a tool with no annotations.

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

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

The description is extremely concise and front-loaded, with no filler words. It uses a compact noun phrase to convey the essential scope. However, it is somewhat under-specified, which slightly reduces the appropriateness of its size—it could be a full sentence without losing conciseness.

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

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

Given the absence of annotations, output schema, and parameters, the description needs to sufficiently explain return values. It lists the major categories (health, version, capabilities) but does not describe the structure or detail of the response. This is adequate for a simple health-check tool but leaves gaps about what 'capabilities' includes and how results are presented.

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

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

The tool has zero parameters, so the input schema is empty. Per rubric, 0 params earns a baseline of 4. The description adds no parameter information, but none is needed since there are no parameters to define.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Server health, version, and capabilities' clearly identifies the tool's scope as a resource (server) and the kinds of information it provides (health, version, capabilities). It is distinct from sibling tools like sensitivity_analysis and run_scenario, which focus on scenario modeling. However, it lacks an explicit verb like 'check' or 'retrieve', making it slightly less direct than ideal.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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. It neither states typical use cases nor mentions any exclusions or conditions. With siblings focused on different tasks, some usage context would help, but none is given.

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

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

With no annotations, the description must disclose behavior. It states the tool 'List all pre-built scenario templates', which implies a read-only operation, and mentions the content categories. However, it does not explicitly confirm there are no side effects, nor describe what happens with an empty template list or how the output is structured. It adds some value but lacks full transparency.

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

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

The description is a single, concise sentence that front-loads the main action and resource. Every phrase adds value: 'all' indicating scope, 'pre-built scenario templates' the resource, and the parenthetical specifics. No wasted words.

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

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

For a zero-parameter, no-output-schema listing tool, the description covers the essential aspects: what is listed and what additional information is included. It does not mention output format or ordering, but given the simplicity, the description is complete enough for an agent to know what to expect.

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

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

The tool has zero parameters and the schema is empty, so schema coverage is effectively 100%. The description goes beyond the schema by explaining what the output includes ('inputs, defaults, outputs', 'custom-scenario format', 'period labels'), which is useful context. Baseline for 0 params is 4, and the description meets that.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List') and the resource ('all pre-built scenario templates'), and differentiates from siblings by specifying that it includes 'inputs, defaults, outputs' plus the 'custom-scenario format and period labels.' This is a specific verb+resource pairing that stands apart from run_scenario or sensitivity_analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies the tool is for discovering available templates and the custom-scenario format, but it does not explicitly state when to use this tool versus alternatives (e.g., before running a scenario) or provide exclusions. Some context is given, but no clear usage directives.

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

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

With no annotations provided, the description carries the transparency burden. It discloses that the tool is '100% deterministic,' a key behavioral trait, and lists the returned components (projections, key_results, assumptions_used, methodology, notes, plain-language explanation). It doesn't explicitly state side effects, but for a simulation tool, determinism and output transparency are meaningful.

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

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

The three-sentence description is front-loaded with the core purpose, includes essential behavioral and output details, and has no fluff. Every sentence earns its place, making it highly efficient.

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

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

Given the tool's complexity (5 parameters, nested objects, no output schema), the description provides a solid overview and lists return fields, which is helpful. However, it omits explicit guidance on choosing this tool versus siblings, and nuances like inputs being passable at top level or unknown-key handling are only in the schema, not the description. Adequate but with gaps.

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

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

Schema description coverage is high (80%), so the baseline is 3. The description adds little beyond what the schema already provides; it mentions the two modes ('template or a free-form metrics model') but doesn't clarify parameter syntax or relationships beyond the schema. Therefore, it doesn't significantly compensate for the 20% gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly identifies run_scenario as the 'Main simulation tool' and specifies its functionality: 'Deterministic what-if projection from a template or a free-form metrics model.' This gives a specific verb (run/project), resource, and distinguishes it from siblings by positioning it as the primary simulation entry point.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description provides minimal usage guidance beyond calling it the 'Main simulation tool.' It doesn't explicitly state when to prefer this over sensitivity_analysis, break_even, compare_scenarios, or other siblings, nor does it mention exclusions. The 'main' label implies primary use, but concrete direction is missing.

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

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

Since no annotations are provided, the description carries the behavioral transparency burden. It discloses the methodology ('one-at-a-time'), the nature of outputs (sweeps, elasticity, ranges, influential inputs), and indicates a read-only analysis operation through its focus on returns. However, it does not explicitly state side effects or prerequisites, which prevents a perfect score.

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

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

The description is only two sentences, with the action front-loaded and the output details following concisely. Every word contributes meaning without redundancy.

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

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

The tool has 12 parameters, no annotations, no output schema, and low schema coverage. The description provides only a high-level overview and omits critical invocation details like how to specify inputs or the target metric, how variables relate to inputs, and what the response structure looks like. It is not sufficiently complete for an agent to invoke the tool reliably.

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

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

Schema description coverage is only 25%, and the description does not map its language ('inputs', 'target output metric') to specific schema properties such as inputs, variables, target_metric, or variation. The mention of 'per-variable sweeps' is the only link to parameters, leaving many parameters semantically unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Vary one or more inputs') and the output ('impact on a target output metric'), specifying the one-at-a-time method. It distinguishes itself from siblings by detailing unique outputs like per-variable sweeps, elasticity estimates, and most influential inputs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description implies when to use this tool (for sensitivity analysis) but does not explicitly contrast it with sibling tools like run_scenario or compare_scenarios. There is no stated alternative or exclusion, so the guidance is implicit rather than explicit.

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