Fitness Tools

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds context about the underlying models (NEAT+EAT vs lookup table), which goes beyond the annotations. No contradictions.

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 core purpose and methods. Every word contributes value with no 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?

With an output schema and no required parameters, the description covers the main two methods effectively. Could be slightly more complete by explaining how the models differ in terms of input requirements, but overall it provides sufficient context for a specialized 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 description coverage is 0%. The description explains occupation/steps for non-exercise and training volume for exercise, which maps to some parameters (occupation, steps_per_day, session_minutes, sessions_per_week). However, parameters like bmr, weight, methods, intensity, activity_level are not explained.

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 estimates the TDEE activity multiplier using two specific methods (classic lookup table or NEAT+EAT model). It distinguishes from sibling tools like tdee (which calculates full TDEE) and adaptive-tdee.

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 mentions two models but does not explicitly guide when to use one over the other or when to prefer this tool over siblings. No when-not-to-use guidance is provided.

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?

Describes how kalman handles missing days, gates outliers, reports CI95 uncertainty, and explains regression/endpoints. Also notes error vs graceful fallback on zero weigh-ins. Adds value beyond readOnlyHint/idempotentHint 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?

Front-loaded with purpose, then method explanation, then usage details. Every sentence adds value, though slightly lengthy. Minor redundancy in referencing methods.

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 main behaviors, constraints, and edge cases (zero weigh-ins). Output schema exists, so return format not needed. For a complex multi-method tool, description is fairly complete, though could mention method selection effect.

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 25% (only prior_tdee_kcal described). Description compensates for entries (requires at least weight or kcal) and methods (explains default and alternatives), but does not fully cover window_days or prior_tdee_kcal details beyond schema.

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?

Clearly states 'Measure actual TDEE from logged history', distinguishes from formula TDEE ('Use instead of formula TDEE'), and lists specific methods (kalman, regression, endpoints).

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?

Explicitly recommends using this tool 'instead of formula TDEE once real logged data exists', provides entry constraints (date span ≤10 years, at least one of weight/kcal), and warns about weigh-in requirements with fallback (methods:'all').

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 indicate readOnlyHint=true, destructiveHint=false, idempotentHint=true, which cover safety. The description ('estimate') aligns with these annotations but adds no additional behavioral context beyond the structured fields.

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?

Single sentence is concise and front-loaded with purpose. However, listing methods without parameter mapping sacrifices some clarity for brevity.

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?

Despite having an output schema, the tool has 9 parameters and multiple methods. The description fails to explain how to choose a method based on available inputs or what the output contains, leaving significant gaps for a complex 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 0%, yet description only mentions method names without clarifying which parameters (e.g., waist, neck, hip for US Navy; skinfold_sum for Jackson-Pollock; age, weight, height for Deurenberg) are required for each. This leaves the agent to guess parameter usage.

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 specifies the tool estimates body-fat percentage and lists three distinct methods (US Navy circumference, Jackson-Pollock 3-site skinfold, Deurenberg BMI-based). It is a specific verb+resource, and no sibling tool overlaps with this function.

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 used for body-fat estimation via given methods, but provides no explicit guidance on when to use each method, prerequisites, or when alternatives (e.g., other anthropometric calculators) may be more appropriate.

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 indicate read-only, idempotent, non-destructive behavior. The description adds context about flagging the natural ceiling (~25) and calculating height-adjusted form, providing extra behavioral insight beyond 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 a single concise sentence that front-loads the action and key output. It is efficient but slightly dense, missing some structural clarity.

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 an output schema present, the description does not need to cover return values. However, it omits explanation of the 'methods' parameter and the required input format (nested objects with units). The flag about natural ceiling is helpful but 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 mentions weight, body fat, and lean mass but does not explain the nested structure of height and weight objects, nor the 'methods' parameter. The default 'all' for methods is not addressed.

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 computes FFMI and its height-adjusted form, with a specific verb and resource. It distinguishes from sibling tools like 'body-fat' or 'muscle-potential' by focusing on a unique metric.

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 weight and body fat (or lean mass) are available, but does not explicitly state when not to use it or provide alternatives. Usage context is clear but lacks exclusions.

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 indicate a safe, idempotent read operation. The description adds useful behavioral context: it computes grams using the g-per-kg-bodyweight method and mentions goal-based protein defaults (which affect output when protein_g_per_kg is not provided). This goes beyond annotations without contradicting them.

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 of 15 words that frontloads the essential information. Every word adds value, and there is no redundancy or fluff.

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 presence of an output schema (not shown but indicated), the description does not need to detail return values. It sufficiently describes the tool's purpose and core inputs. The omission of the 'methods' parameter is a minor gap, but overall the description is adequate for understanding what the tool does.

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 0% schema description coverage, the description must explain parameters. It covers 'calories', 'weight', 'goal', and implied 'protein_g_per_kg' and 'fat_g_per_kg' via the bodyweight method. However, it does not mention the 'methods' parameter, which is complex (anyOf array/string with default 'all'). This leaves a notable gap for a tool with six parameters.

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 verb 'Compute', the resource 'protein/fat/carb grams for a calorie target', and the method 'g-per-kg-bodyweight with goal-based defaults'. This is specific and distinguishes from sibling tools like tdee or body-fat, which have different purposes.

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 converting a calorie target into macronutrient grams based on bodyweight and fitness goal. It does not explicitly state when not to use it or compare to alternatives, but the context is clear enough for an agent to understand appropriate use cases.

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=true and idempotentHint=true. The description adds value by naming the three models used and noting 'Men only in v1', which is a behavioral constraint beyond the 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 a single sentence that efficiently fronts the purpose and key model references. It could be slightly more structured but remains concise with no redundant 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?

Given 6 parameters, an output schema (not shown), and multiple models, the description provides essential context but omits details like parameter dependencies (e.g., wrist/ankle only for Casey Butt) and the contradiction between 'Men only' and the schema allowing female.

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 0% schema description coverage, the description must compensate. It mentions wrist+ankle and target body fat, providing context for those parameters. However, it does not explain height or sex parameters fully, and the 'Men only' note conflicts with the sex enum including 'female'.

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 estimates drug-free maximum bodyweight at a target body fat percentage using three named models (Casey Butt, FFMI, Berkhan). It distinguishes from sibling tools like ffmi or tdee which focus on current metrics, not potential.

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 for drug-free potential estimation but does not explicitly state when to use this tool versus alternatives like ffmi or body-fat. No exclusion or comparison 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 indicate read-only and idempotent behavior. The description adds value by specifying the estimation formulas (Epley, Brzycki, etc.) and the output type (%1RM load chart), which goes beyond what annotations convey. No contradiction.

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 sentence front-loaded with the key action, listing formulas efficiently. Every word adds value with no 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 description covers the core estimation and output but lacks parameter details (especially 'methods') and usage guidance. Given the complexity (multiple formulas, nested object), more context is needed for full completeness.

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 0% schema coverage, the description must compensate. It mentions 'submaximal set' implying weight and reps but does not describe the 'methods' parameter nor clarify the weight object structure (value and unit). The parameter semantics are largely 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 it estimates one-rep max from a submaximal set using six named formulas and returns a %1RM load chart. This specific verb+resource combination distinguishes it from sibling tools like 'tdee' or 'body-fat'.

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 tool is for estimating 1RM using submaximal weights, but does not explicitly state when to use it versus alternatives (e.g., 'powerlifting-attempts'). No exclusions or context for tool selection is provided.

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?

Beyond annotations (readOnly, idempotent), description adds determinism and outputs (warmup, plate loading). No contradictions.

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?

Two sentences, front-loaded with key output, no extraneous 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?

With output schema and annotations, description covers main outputs and safety traits. Adequate for a read-only deterministic 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 description coverage is 0%; description mentions aggressiveness and available plates but not bar_weight or one_rep_max structure. Incomplete for 4 parameters.

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 states deterministic opener/second/third attempts from 1RM, plus warmup and plate loading. Distinguishes from sibling tools like one-rep-max.

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?

Implied usage for meet attempt calculation but no explicit guidance on when to use vs alternatives or prerequisites.

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=true, idempotentHint=true, destructiveHint=false, indicating safe, non-destructive use. The description adds value by specifying the estimation sources (DXA/anthropometric) and cutoff criteria, providing behavioral context beyond the 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 a single, somewhat long sentence that packs all key information. It is front-loaded with the purpose and estimation sources. No redundant phrases, but breaking into multiple sentences could improve readability slightly.

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 complexity (6 parameters, nested objects, multiple estimation methods, and multiple cutoffs), the description covers the main aspects. It mentions the two estimation methods and the three cutoffs. The presence of an output schema means return values do not need explanation. It does not clarify behavior when both estimation methods are provided, which is a minor gap.

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 explains that 'asm_kg' is the DXA value and the anthropometric estimate uses the other parameters (sex, height, weight, age). The 'methods' parameter is mentioned only indirectly. This adds meaningful context, though explicit enumeration of methods values would improve clarity.

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 estimates RSMI from DXA or anthropometric estimate (Wen 2011), and flags against specific sarcopenia cutoffs (EWGSOP2, AWGS, Baumgartner). This distinguishes it from sibling tools like body-fat or ffmi, which target different aspects of body composition.

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 for muscle mass assessment and sarcopenia screening, providing clear context. However, it does not explicitly state when not to use or name alternative tools; the sibling list and tool name make it clear this is specific to RSMI and sarcopenia.

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, idempotentHint, and destructiveHint. The description confirms it's a read estimation but adds little beyond noting the LBM method unlock. No contradictions.

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?

Two concise sentences, front-loaded with key purpose and followed by a conditional guideline. No waste.

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 complex tool with 8 parameters, nested objects, and multiple equations, the description is too brief. It doesn't explain activity levels, the methods parameter, or expected output (though output schema exists).

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 0%, so the description must compensate. It only mentions body_fat and lean_mass, ignoring the other 6 parameters (sex, age, height, weight, activity, methods) which have enums and nested structures.

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 explicitly states the tool estimates BMR and TDEE via four named equations, with a clear resource (estimation methods) and verb (estimate). It distinguishes from siblings by specifying the exact equations used.

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 by mentioning 'provide body_fat or lean_mass to unlock the LBM-based methods,' but does not explicitly state when to use this tool versus alternatives like adaptive-tdee or activity-multiplier.

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