TruePeptideSource

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered; the description adds that the tool returns units to draw plus per-component amounts, which is real output context. It does not mention error behavior (e.g., unknown blend name, dose exceeding vial contents) or how ambiguity in composition resolution is reported.

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 what is computed, then the invocation rule. The parenthetical blend examples are dense but each earns its place by anchoring the tool to concrete real-world inputs.

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 9 parameters, no output schema and no annotations about results, the description does the necessary work of saying what comes back (draw units, per-peptide amounts). Gaps remain around failure modes and the composition-version fallback, though the latter is documented in the 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?

Schema coverage is 100%, so the baseline is 3, but the description goes beyond the schema by explaining the joint semantics of the two dosing modes: dose applies to targetPeptide by default or to the entire blend when totalDose is set. It also frames blend-vs-components as alternative inputs, which clarifies how those two mutually exclusive-feeling parameters interact.

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 computation ('math for vials holding two or more peptides') and names the two outputs: units to draw and per-peptide amount delivered per draw. The 'two or more peptides' scope cleanly separates it from the single-peptide peptide_reconstitution_calculator sibling, and concrete blend examples (KLOW, GLOW, BPC-157 + TB-500) make the domain unmistakable.

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 a clear invocation recipe: name a known blend or list components, then supply a dose for either targetPeptide or the whole blend via totalDose. It implies the single-peptide case belongs elsewhere but never names peptide_reconstitution_calculator or peptide_supply_calculator as alternatives, so there is no explicit when-not-to-use routing.

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 carry readOnly, idempotent, non-destructive and closed-world hints, so the safety profile is fully covered. The description adds one genuinely new trait, 'each labelled by origin' (provenance attribution), but says nothing about failure behavior for unrecognized peptides or about depth/length of the result.

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 tight sentence with the operation front-loaded and the compared fields enumerated in a readable list. Every clause carries information; no 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 usefully enumerates the fields returned and their provenance labelling, which is exactly what an agent needs to know before calling. The remaining gap is the absent handling of unknown or ambiguous peptide names.

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%, with both `a` and `b` documented and exemplified, so the description's examples (semaglutide vs tirzepatide) largely duplicate them. It adds only the implicit constraint that exactly two items are compared, with no note on whether order matters or blends are allowed beyond the schema example.

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 (side-by-side comparison) and resource (two peptides) plus the comparison axes it covers: evidence, FDA status, half-life, routes, vial sizes, storage, dose ranges. It is clearly distinguishable from single-item tools like peptide_lookup or peptide_search, though it never names those siblings explicitly.

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 is implied by 'comparison of two peptides' and the worked examples, so an agent can infer this is the tool for head-to-head questions. There is no explicit when-to-use/when-not or routing to peptide_lookup for single-peptide questions, and no guidance on what happens when a name is not found.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds genuine value by disclosing result structure the agent could not otherwise know – dose rows carry an origin label (clinical study, guide, community-reported, regulatory) plus sources and page links, which tells the agent how much to trust the data.

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 dense sentences with zero filler. The one-peptide scope is front-loaded, and the provenance note about dose rows follows immediately where it is useful.

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 carries the burden of describing returns, and it does so well by listing the content areas and the provenance metadata attached to each dose row. It stops short of explaining pagination or whether the response is section-grouped, which a caller assembling a prompt would want.

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 both the peptide identifier and the sections enum are fully documented in structured form, making 3 the baseline. The description echoes the section names (reconstitution, side effects, storage, stacking, community) which reinforces the enum but adds no syntax or default behavior beyond it.

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-resource pairing ("look up a peptide") and enumerates exactly what content comes back: dosing, reconstitution, side effects, storage, half-life, FDA status, stacks, community reports. The phrase "for questions about one peptide" implicitly separates it from peptide_compare, but it never names the sibling directly, so the boundary is inferred rather than stated.

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?

"For questions about one peptide" gives a usable trigger condition and quietly contrasts with the multi-peptide siblings. However, there is no explicit guidance on when to reach for peptide_search first, or when peptide_compare is the better route, leaving the agent to guess at the discovery-vs-retrieval boundary.

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 establish that this is a read-only, idempotent, non-destructive, closed-world operation. The description adds meaningful behavioral detail beyond that: it flags likely mg/mcg mix-ups against published ranges and returns a calculator link, which tells the agent what to expect from the response.

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 front-load the core calculation scope, then follow with the range-check behavior and return value. Every sentence adds information; there is no 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 an 8-parameter calculator with three modes and no output schema, the description covers the main input modes, the optional peptide behavior, and the returned link. It does not spell out the structure of the numeric results, but the essential invocation context is present.

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, but the description adds mode-level semantics: dose versus unitsDrawn are alternative inputs, and supplying peptide adds an IU factor, a range check, and published injected ranges. This clarifies how parameters interact in ways the flat schema does not.

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 (single-peptide vial reconstitution) and verb (exact math), and enumerates the three supported calculations: syringe units for a dose, concentration/doses per vial, and dose held in given units. 'Single-peptide vial' also implicitly distinguishes it from the peptide_blend_calculator sibling.

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?

Clear context is given: it is for single-peptide vial math, with the optional peptide parameter triggering range checks. It does not explicitly name alternatives like peptide_blend_calculator or peptide_supply_calculator, so the agent must infer that blends belong elsewhere, but the scope is otherwise clear.

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, closed-world behavior, so the safety profile is covered. The description adds genuine value by disclosing what each result contains: names, one-line summaries, FDA status, evidence level and page links. It does not mention result caps or pagination, which keeps it below a 5.

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, zero filler, and the matching scope is front-loaded before the return-value summary. Every clause carries information an agent can act on.

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 correctly compensates by enumerating returned fields, and it covers both parameters implicitly. The only gap is absence of any guidance on result volume or how to narrow a too-broad topic query, which matters for a search tool whose default lists everything.

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 both parameters are already fully documented in the schema, including the empty-string-lists-everything behavior. The description's topic examples (GLP-1, healing, weight loss, sleep) largely repeat the schema's own examples, adding little beyond it. Baseline 3 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?

States a specific verb and resource ('Lists the peptides TruePeptideSource covers') plus the matching dimension (name, alias, topic). It's clearly a discovery/search tool, but it never names how it differs from the closest sibling, peptide_lookup, leaving the search-vs-lookup boundary to inference.

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 is implied: agents can infer this is the entry point for discovering peptides by topic or name, while peptide_lookup would fetch a specific record. However, there is no explicit 'use this when...' statement and no mention of alternatives among the five siblings (compare, blend/reconstitution/supply calculators).

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 cover the read-only/idempotent/non-destructive profile, so the description adds genuine behavioral context on top: it counts whole doses (a rounding rule) and caps usable doses by the mixed-vial shelf life taken from the dataset. It stops short of stating edge-case behavior (e.g., what happens when a vial cannot cover a single dose).

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 tight sentences, front-loaded with the purpose and then the behavioral caveats. No filler and nothing repeated from the title or 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?

With no output schema, the description usefully enumerates what comes back (duration, vial count, three cost figures), which is the key thing an agent needs. It omits return units/currency conventions and how whole-dose rounding affects the cost figures, which would matter for interpreting 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 coverage is 100%, so the schema already documents all nine parameters, including the useWithinDays override. The description reinforces the conditional link between peptide and shelf life/IU factor but adds no format or unit detail beyond the schema, so the baseline 3 applies.

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 (plans) plus the exact outputs: vial duration, vials per cycle, and cost per dose/week/cycle. That output list implicitly separates it from peptide_reconstitution_calculator and peptide_blend_calculator, but no sibling is named explicitly.

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?

Conditional guidance exists ('when pricePerVial is given' for cost answers, 'from the dataset when a peptide is named'), but there is no statement of when to choose this tool over the reconstitution or blend calculators. Usage must be inferred from the described outputs.

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