PK serum simulation, reconstitution math and compound data for agents. Paid tools $0.01 via x402.
Scored across 5 tools
Each tool has a clearly distinct purpose: get_compound retrieves a single record, list_compounds enumerates all, recon_calc calculates specific reconstitution math, recon_suggest provides ranked suggestions, and simulate generates pharmacokinetic curves. There is no overlap or ambiguity between them.
All tool names follow a consistent verb_noun pattern with snake_case: get_compound, list_compounds, recon_calc, recon_suggest, simulate. The abbreviations 'recon' are used consistently, and the pattern is predictable across the set.
With 5 tools, the set is well-scoped for a domain covering compound lookup, reconstitution math, and pharmacokinetic simulation. Each tool addresses a distinct aspect of the workflow without redundancy or bloat.
The tool surface covers the core needs: retrieval of individual and all compounds, reconstitution calculations and suggestions, and simulation of serum levels. Given the read-only nature (outputs are for relay to humans), the absence of update/delete tools is appropriate and does not create dead ends.
Full published record for one compound, looked up by canon id, slug or alias (slug and alias matching is case-insensitive). Outputs are for relay to a human decision-maker; not for autonomous administration.
| Name | Required | Description | Default |
|---|---|---|---|
| compound | Yes | Canon id, slug, or alias. |
| Name | Required | Description |
|---|---|---|
| compound | Yes | The published canon record, verbatim. |
| editorial | Yes | |
| disclaimer | Yes | Fixed disclaimer. Relay it with any output. |
| intended_use | Yes | Fixed intended-use statement. Relay it too. |
| reconstitutable | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It adds important context: outputs are meant for relay to a human decision-maker and not for autonomous administration, and slug/alias matching is case-insensitive. This gives the agent meaningful guidance beyond the schema, though it does not explicitly state lack of side effects.
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 two sentences with no filler. The core lookup behavior is front-loaded, followed by a useful caveat about usage context. Every sentence contributes.
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 single-parameter read-style tool with an output schema, the description is complete: it specifies the input forms, case-insensitivity behavior, and a usage constraint. Nothing critical is missing for an agent to invoke it correctly.
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 coverage for the compound parameter is 100%, so the baseline is 3. The description adds value by clarifying that matching is case-insensitive for slug and alias, which is a useful behavioral detail about how the parameter is interpreted.
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 states a specific verb and resource: it retrieves the 'Full published record for one compound' by identifier. It also distinguishes itself from sibling list/calculation tools by emphasizing a single compound lookup, making its role clear.
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 use when a complete record for a specific compound is needed and gives lookup identifiers, but it does not explicitly state when to prefer this tool over list_compounds, recon_calc, or simulate. Usage is implied rather than directly compared against alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List every published compound with its class, terminal half-life in days, administration routes and whether reconstitution math is available for it. Takes no arguments. Outputs are for relay to a human decision-maker; not for autonomous administration.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| compounds | Yes | |
| disclaimer | Yes | Fixed disclaimer. Relay it with any output. |
| intended_use | Yes | Fixed intended-use statement. Relay it too. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool takes no arguments and explicitly constrains output usage to human decision-making, not autonomous administration. It implies a read-only listing operation, though it does not explicitly state side-effect freedom or data source.
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, well-structured sentence that front-loads the action and output fields, then adds the no-arguments fact and the usage constraint. Every clause earns its place; there is no redundancy or filler.
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 listing tool with an output schema present, the description is complete. It specifies scope ('every published compound'), key output attributes, that no arguments are needed, and how the results should be used. Nothing essential is missing for an agent to invoke it correctly.
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?
There are zero parameters and the schema already reflects this with an empty properties object. The description reinforces this by stating 'Takes no arguments,' which is helpful for an agent scanning quickly. Baseline 4 is appropriate for a no-parameter tool.
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 ('List') and resource ('every published compound'), and enumerates the exact fields returned: class, terminal half-life, administration routes, and reconstitution math availability. This clearly distinguishes it from siblings like get_compound (single lookup), recon_calc (calculation), and simulate (modeling).
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 gives clear context: outputs are for relay to a human decision-maker and not for autonomous administration. This is an explicit when-not-to-use for autonomous actions, though it does not name alternative tools or specify when to prefer this over siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Paid: $0.01 USDC per call via x402 (payment in _meta["x402/payment"]). Reconstitution math for one vial and one target dose: the concentration to reconstitute to, the bacteriostatic water to add, what one dose reads on a U-100 syringe, and how many doses the vial yields. Exactly one target-dose field must be present; unknown fields are rejected. Outputs are for relay to a human decision-maker; not for autonomous administration.
| Name | Required | Description | Default |
|---|---|---|---|
| draw_ml | Yes | The volume you want to DRAW for one dose, in mL -- not the vial fill. Accepted range is one hundredth of a mL up to ten mL. The fill needed to make that true comes back as bac_water_ml. | |
| vial_mg | Yes | Total mass in the vial, mg. Positive. | |
| cost_usd | No | Vial cost, zero or more. Omitted, cost_per_dose_usd is null. | |
| frequency_days | No | Days between doses, positive. Feeds days_per_vial only. Defaults to one. | |
| target_dose_mg | No | Target dose, mg. Positive. | |
| target_dose_mcg | No | Target dose, mcg. Positive. |
| Name | Required | Description |
|---|---|---|
| meta | Yes | |
| disclaimer | Yes | Fixed disclaimer. Relay it with any output. |
| residual_mg | Yes | |
| bac_water_ml | Yes | |
| intended_use | Yes | Fixed intended-use statement. Relay it too. |
| days_per_vial | Yes | |
| syringe_marks | Yes | |
| doses_per_vial | Yes | |
| units_per_dose | Yes | |
| cost_per_dose_usd | Yes | |
| concentration_mg_per_ml | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and discloses a $0.01 USDC per-call payment via x402, strict field validation behavior, and a usage limitation (not for autonomous administration). This goes well beyond what the schema provides. It does not explicitly state the tool is read-only, but as a pure calculation that is reasonably inferable.
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?
Three dense sentences deliver payment info, purpose, outputs, validation constraints, and usage scope with zero redundancy. The most critical operational detail (payment) is front-loaded.
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?
An output schema exists, parameters are fully documented, and the description adds payment, validation, and output-usage context. The only meaningful gap is explicit guidance for selecting this tool versus sibling tools; otherwise an agent has enough to invoke it correctly and interpret the results.
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 100%, so each parameter is already well described. The description adds the important cross-parameter rule that exactly one target-dose field must be present and that unknown fields are rejected, which clarifies how target_dose_mg and target_dose_mcg relate and is not captured by the schema's required list.
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 tool performs reconstitution math and enumerates the outputs (concentration, bacteriostatic water to add, U-100 syringe reading, doses yielded). It uses a specific verb and resource, though it does not explicitly distinguish itself from the sibling tools get_compound, list_compounds, or simulate.
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 gives a hard usage constraint: 'Exactly one target-dose field must be present; unknown fields are rejected.' It also scopes outputs to relay to a human decision-maker, not autonomous administration. It does not, however, state when to prefer this tool over its siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Paid: $0.01 USDC per call via x402 (payment in _meta["x402/payment"]). Ranked reconstitution suggestions for one published reconstitutable compound: bacteriostatic-water presets that put the published per-administration dose range's clean steps on whole U-100 syringe marks. Vial defaults to the compound's first published strength. Compounds whose published range is denominated per period are refused rather than guessed at. Unknown fields are rejected. Outputs are for relay to a human decision-maker; not for autonomous administration.
| Name | Required | Description | Default |
|---|---|---|---|
| vial_iu | No | Your actual vial's total activity, IU, positive. Only for compounds whose published vials are IU-quantified. Omitted, the first published vial strength is used. | |
| vial_mg | No | Your actual vial's total mass, mg, positive. Only for compounds whose published vials are mg-quantified. Omitted, the first published vial strength is used. | |
| compound | Yes | Canon id, slug, or alias. Must be a reconstitutable compound. |
| Name | Required | Description |
|---|---|---|
| meta | Yes | |
| rows | Yes | Ranked presets, best first, at most 3 rows. An empty array means no clean-graduation preset exists for this vial -- a real answer, not a refusal. |
| vial | Yes | |
| compound | Yes | |
| disclaimer | Yes | Fixed disclaimer. Relay it with any output. |
| intended_use | Yes | Fixed intended-use statement. Relay it too. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full responsibility for behavioral disclosure and does a solid job: it discloses the payment mechanism and metadata field, refusal behavior for per-period compounds, rejection of unknown fields, and the non-autonomous output constraint. It does not discuss error handling or rate limits, but for a suggestion tool these are not critical omissions.
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 dense and information-bearing; every sentence contributes a constraint, behavior, or usage note. It is somewhat long, but there is no fluff, and the payment note is arguably important front-loaded context for an agent deciding whether to call the tool.
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 combination of the detailed description and the presence of an output schema gives an agent most of what it needs: purpose, constraints, refusal cases, and parameter semantics are covered. Minor gaps like the exact meaning of 'ranked' or error responses are either outside description scope or sufficiently supported by the output schema.
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 input schema already documents all 3 parameters with descriptions, so the baseline is 3. The description's 'Vial defaults to the compound's first published strength' mirrors the schema's 'Omitted, the first published vial strength is used,' adding little incremental meaning beyond what structured data already provides.
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 states a specific action ('Ranked reconstitution suggestions') and resource ('one published reconstitutable compound'), with concrete detail about the output ('bacteriostatic-water presets... on whole U-100 syringe marks'). It clearly differentiates from get_compound and list_compounds by being suggestion-oriented, but it never explicitly contrasts with recon_calc, so it stops short of full sibling differentiation.
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 gives clear usage constraints: single published compound, vial defaults, refusal of per-period compounds, rejection of unknown fields, and a warning that outputs are not for autonomous administration. However, it does not name alternatives such as recon_calc or state when to prefer this tool over them, leaving sibling selection to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Paid: $0.01 USDC per call via x402 (payment in _meta["x402/payment"]). Pharmacokinetic serum curve for one compound at one dose and one cadence, over a requested horizon. Exactly one dose field must be present; unknown fields are rejected rather than ignored. Outputs are for relay to a human decision-maker; not for autonomous administration.
| Name | Required | Description | Default |
|---|---|---|---|
| route | No | One of the compound's published routes. Omitted, its primary route is used. | |
| dose_iu | No | Dose per injection in the compound's activity unit. Positive. Requires a published conversion for that compound. | |
| dose_mg | No | Dose per injection, milligrams. Positive. | |
| compound | Yes | Canon id, slug, or alias. | |
| dose_mcg | No | Dose per injection, micrograms. Positive. | |
| duration_weeks | Yes | Length of the dosing window, whole weeks, from one to two hundred and sixty. The model always adds a sixty-day washout tail. | |
| samples_per_day | No | Sample resolution of the returned series, whole samples, from one to twenty-four. Defaults to twenty-four. | |
| injections_per_week | Yes | Injections per WEEK -- not per day; the name is the contract. Accepted range is a quarter of an injection per week up to twenty-one per week. |
| Name | Required | Description |
|---|---|---|
| meta | Yes | |
| units | Yes | The ONLY correct label for the numbers in `level`. |
| series | Yes | |
| compound | Yes | |
| disclaimer | Yes | Fixed disclaimer. Relay it with any output. |
| intended_use | Yes | Fixed intended-use statement. Relay it too. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses payment requirement, strict handling of unknown fields, and the intended non-autonomous use of outputs. This adds meaningful behavioral context beyond the schema, though it does not cover potential side effects or exact failure modes.
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?
Three dense sentences, each earning its place: payment cost, core function, and critical validation rules plus use-case framing. No fluff, no repetition of schema details, and the most operationally important constraint is highlighted.
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 an output schema exists, the description need not explain return values. It covers payment, validation strictness, and output suitability. Minor gaps remain, such as whether any compound-specific requirements must be met or how errors surface, but the overall context is sufficient for most agents.
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 coverage is 100%, so the baseline is 3. The description adds a critical cross-parameter rule: 'Exactly one dose field must be present,' which is not defined in the schema. This helps the agent avoid ambiguous or invalid calls and compensates for the absence of this constraint in structured metadata.
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?
States a specific verb and resource: 'Pharmacokinetic serum curve for one compound at one dose and one cadence, over a requested horizon.' This clearly distinguishes it from siblings like get_compound and list_compounds, which are lookup tools, and recon_calc, which likely performs calculations but not simulation.
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?
Implies usage through constraints like 'Exactly one dose field must be present' and 'Outputs are for relay to a human decision-maker; not for autonomous administration,' indicating a decision-support context. However, it does not explicitly state when to prefer this tool over siblings, nor mention any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
recon_suggestget_compoundlist_compoundsrecon_calcsimulateDeterministic peptide reconstitution and dosing math, so assistants compute it instead of guessing.
Scientific compute for AI agents: symbolic, numerical, quantum, chemistry, ODE. Paid via x402.
x402-paid agent tools: 18 over HTTP, 14 over stdio. USDC per call, no API key.
16 paid Base data tools for agents over MCP, paid per call in USDC via x402.
Add one secure layer between your agents and this server.