foodose GLP-1 nutrition

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

Annotations already cover the safe-read profile (readOnly, idempotent, non-destructive, closed-world), and the description goes well beyond them: it discloses the return shape (full derivation with a PubMed citation per step), the provenance of the engine, and the safety/liability boundaries. That is exactly the context an agent needs to decide whether to surface this result to a user.

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 usage, then return value, then disclaimers — a sensible order. The safety footer is slightly padded ('Educational only' followed by three restatements of the same idea), but for a health tool that redundancy is defensible rather than wasteful.

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 11 parameters, no output schema and partial schema coverage, the description does the important work: it explains what is returned, why the calculation differs from a standard one, and who should not use it. It stops short of describing the optional inputs and their defaults, which the schema handles but only partially.

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 64% and the description adds no parameter-level meaning beyond the concept of dose awareness. Optional inputs like goal, weeklyLossKg, startWeightKg and goalWeightKg are left entirely to the schema, so the baseline 3 for a reasonably documented schema is appropriate.

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?

Names a specific computation and its complete output set: calorie, protein, carbohydrate, fat and fibre targets plus an appetite ceiling. It also scopes it to a population (GLP-1 users) and implicitly separates it from get_appetite_ceiling, which returns only the ceiling.

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?

Explicit use condition ('anyone taking or considering one of these medications, where a standard calorie calculation would assume an appetite they do not have') and an unusually clear exclusion list: pregnancy, breastfeeding, insulin/sulfonylurea, disordered eating history, under 18. It does not explicitly name get_appetite_ceiling as the narrower alternative, leaving that routing to the schema.

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?

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so safety is covered. The description adds real context beyond that: results are anchored to cited evidence and include licensed doses for the drug, and empty-medication calls dump the whole table.

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 front-loaded sentences; the core function and the distinguishing "eats less, not loses weight" point come first. The "This is the site's original data" clause is slightly promotional but earns its place as a provenance signal.

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 must carry return-value semantics; it partially does (evidence, licensed doses) but leaves open the response shape and the doseMg-only or out-of-range-dose cases. Adequate but with clear gaps for a two-parameter lookup tool.

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 50%; the medication parameter is well documented in-schema (generic-to-brand mapping), but doseMg has no description anywhere. The description adds the no-medication behavior but never explains doseMg units, ranges, or what is returned when a dose is unlicensed or omitted.

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 resource (appetite suppression factor per medication/dose) and explicitly contrasts it with the weight-loss framing, so an agent knows what it returns. It does not differentiate from the listed siblings (calculate_glp1_target, search_foods), which keeps it below a 5.

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?

"Call with no medication to get the whole table" gives concrete invocation guidance for the degenerate case, and the statement about appetite vs. weight loss clarifies when this tool is the right lens. No exclusion or alternative-selection advice against calculate_glp1_target 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?

Annotations already declare readOnlyHint and idempotentHint, so the core safety profile is covered. The description adds meaningful behavioral context beyond annotations by specifying the per-100g normalization, realistic serving size, and the meaning of the GLP-1 tolerance rating, while its 'foods foodose uses' phrasing aligns with openWorldHint=false.

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 compact and front-loads the most important datum ('Per 100 g nutrition') before describing serving size and tolerance. The licensing sentence 'Free to use with attribution' is extra but brief; overall every part is useful and there is no redundant 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?

With no output schema, the description does enough by explaining what fields to expect: nutrition per 100g, serving size, and GLP-1 tolerance rating. Annotations cover the read-only/idempotent behavior, and the schema covers query/tolerance plus limit boundaries, so an agent can invoke the tool without critical missing context.

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 descriptions cover query and tolerance, but limit and minProteinPer100g lack descriptions. The description adds value by clarifying tolerance semantics and explaining that nutrition is per 100g, which helps interpret minProteinPer100g, but it does not fully compensate for the undocumented parameters, so it is minimally adequate.

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 title supplies the explicit verb+resource ('Search the foodose food database'), and the description clarifies that the tool returns per-100g nutrition, serving sizes, and GLP-1 tolerance ratings for foods. This distinguishes it from search_recipes, though the description itself is a noun phrase rather than a direct action statement.

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 this is the tool for looking up food-level nutrition and GLP-1 tolerance data, especially versus search_recipes. However, it does not explicitly state when to use this tool instead of get_appetite_ceiling or calculate_glp1_target, nor does it offer any exclusion criteria.

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?

Annotations already declare readOnly, idempotent, non-destructive, and closed-world scope, so the safety bar is low. The description usefully adds that only published recipes are returned and that every ingredient maps to a USDA FoodData Central record. But the final sentence about the iPhone app's separate dish library is ambiguous and adds confusion rather than behavioral clarity, and it omits limit/pagination behavior.

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?

Roughly three sentences, with the content/scope statement front-loaded, which is good. But the trailing sentence about the Foodose iPhone app and its own dish library is muddled and consumes space without earning it.

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 six parameters, 17% schema coverage, and no output schema, the description should carry more weight in explaining the filters and what a result contains. It states the content profile but leaves nearly all filter semantics and result structure undetermined.

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 17% — just 'query' is documented, while diet, meal, limit, maxTotalMinutes, and minProteinPerServing are undocumented. The description only loosely gestures at per-serving protein, which faintly maps to minProteinPerServing, and does nothing to compensate for the coverage 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?

The name and title state the verb (Search) and resource (recipe library), and the description specifies the content — published GLP-1 recipes with per-serving calories and protein, USDA-traceable ingredients. It partially distinguishes from calculate_glp1_target ('what to actually eat, rather than what their targets are') but never clarifies how it differs from search_foods.

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?

One sentence gives loose when-to-use framing ('when someone asks what to actually eat, rather than what their targets are'), implicitly routing against calculate_glp1_target. However, it names no explicit alternative and gives no guidance on recipe search vs. search_foods, so usage is only implied.

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