Turn a list of supplements into one custom daily supplement from Picardo, with a link to buy it.
Scored across 2 tools
The two tools have clearly distinct roles: one searches ingredient metadata, the other drafts a custom supplement formula. An agent can easily determine which to call based on whether it needs ingredient IDs or a finished formula. There is no meaningful overlap in purpose.
Both names follow the same snake_case verb_noun pattern: search_supplement_ingredients and draft_supplement_formula. The convention is predictable and readable throughout the small set.
Two tools cover the minimal workflow, but the surface feels thin for a supplement-building server. It lacks any browsing, saved-formula, or additional exploration operations that would make the set feel well-scoped rather than narrowly functional.
The core lifecycle is covered: look up ingredients, then draft a custom formula with a purchase link. Minor gaps exist, such as no way to browse or list all available ingredients without already knowing names, but agents can work around this by searching specific ingredient names.
Turn a list of supplements into one custom supplement and a link to review and buy it on picardo.health. Pass each item as the person named it, with its amount and unit, and the ingredient_id from search_supplement_ingredients. Give the amount in the ingredient’s own unit from search; grams, milligrams and micrograms convert automatically, anything else, IU included, does not. Nothing is bought or saved here. Returns what the supplement contains, items that could not be included and why, amounts above or below what one daily serving can hold, capsules a day, the one-time price for a 60-day supply before shipping and tax, and the link. Takes ingredient names and amounts only, no health information. Purchases are for adults 18 and over, shipped within the United States. If the person says they are under 18 or live outside the United States, do not call this tool; explain that Picardo cannot sell to them.
| Name | Required | Description | Default |
|---|---|---|---|
| form | No | capsules | |
| items | Yes |
| Name | Required | Description |
|---|---|---|
| url | Yes | Null when nothing could be included. |
| form | Yes | |
| formula | Yes | What the link contains. |
| priceUsd | Yes | One-time price in US dollars for the whole supply, before shipping and tax. Null when no price is available here; the review page shows it. |
| nextSteps | Yes | |
| unmatched | Yes | Items left out of the link, and why. |
| daysSupply | Yes | |
| outOfRange | Yes | Items left out because the amount is above or below what one daily serving can hold. |
| capsulesPerDay | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces rather than contradicts them by stating nothing is bought or saved. It adds real behavioral detail beyond the annotations: automatic conversion only for grams/milligrams/micrograms (IU and other units do not convert), flagging of amounts outside a daily serving, items that could not be included and why, and the fact that price is pre-shipping and pre-tax.
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?
Front-loaded with purpose, then rules in a logical order: input format, unit conversion, non-effects, outputs, eligibility. It is dense but mostly earns its sentences; the enumerated return contents partially duplicate the opening 'link to review and buy' phrase and the existing output schema.
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?
Covers the hard parts an agent could get wrong — unit conversion limits, no-save semantics, age and geography restrictions — and an output schema already exists so the return-value list is supporting detail. The one material omission is any mention of the form parameter that controls capsule vs powder output.
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?
With schema description coverage at 0% for the top-level parameters, the description compensates well for items by explaining that each entry is the person's own naming, its amount/unit, and the ingredient_id from search. However, the form parameter (capsules vs powder) is never mentioned anywhere in the description or the schema, leaving a real semantic 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?
Opens with a concrete verb and output: turn a list of supplements into one custom supplement plus a review/purchase link on picardo.health. It also names its sibling search_supplement_ingredients as the source of ingredient_id, so an agent can separate the two tools without opening either schema.
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?
Gives explicit preconditions and an explicit exclusion: purchases are for adults 18+ shipped in the US, and if the person is under 18 or outside the US the tool must not be called, with instructions on what to say instead. It also directs the agent to search_supplement_ingredients for the ingredient_id before calling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up ingredients Picardo can put in a custom supplement by name, for example "magnesium glycinate", "vitamin D3" or "fish oil". Takes several names at once. Returns each ingredient’s ID for draft_supplement_formula, the unit its amount is measured in, a typical daily amount and the most one daily serving can hold.
| Name | Required | Description | Default |
|---|---|---|---|
| names | Yes |
| Name | Required | Description |
|---|---|---|
| results | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description adds the result shape (ID, unit, typical daily amount, per-serving maximum), but does not say what happens on a partial or zero match — a meaningful omission for a batch lookup.
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 tight sentences, front-loaded with the action and examples, then batching, then return payload. Nothing is repeated and every clause carries information an agent would not get from the schema alone.
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 one-parameter read tool with full annotation coverage and an output schema, the definition covers purpose, batching, and downstream use adequately. The gaps are the no-match/partial-match behavior and the batch size limit, both of which an agent could hit in practice.
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 carry the meaning of the single `names` parameter. It does convey that these are ingredient names and that multiple may be passed at once, with examples clarifying expected phrasing, but it never mentions the 20-item cap or name length bounds now enforced by the schema — baseline 3 is right.
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 names a specific verb and resource ("look up ingredients ... by name") and anchors it with three concrete examples ("magnesium glycinate", "vitamin D3", "fish oil"). It also distinguishes itself from the only sibling by stating the returned ID is input for draft_supplement_formula, so an agent can place it in the workflow without opening either schema.
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?
Usage context is clear: resolve ingredient names before drafting a formula, and batch several names in one call ("Takes several names at once"). There is no explicit when-not-to-use clause or note about what to do when a name is unrecognized, which keeps it below a 5.
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.
draft_supplement_formulasearch_supplement_ingredientsFind Picardo's clinician-designed blood test panels and Labcorp tests, and get an order link.
Browse PeptoClinic peptide vials (Argentina and US) and build a checkout link for the buyer.
Dietary supplement register: compositions, country upper limits, US prices, stack check vs limits.
Supplements at cost-plus, your Gabriel health and routine, care search and clinician-reviewed Rx.
Add one secure layer between your agents and this server.