PepEvolution Peptide Sources

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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering safety. The description adds meaningful behavior details: fuzzy case-insensitive input matching, return components (PepScore, lab-verified COA, red/green flags, affiliate-tracked link, coupon), and the 'not evaluated' fallback. No contradiction with 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?

Three tight sentences: the first states the core purpose, the second lists output specifics, the third gives usage examples. No redundant phrasing, front-loaded with the main action, and 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 tool with one simple parameter, strong readOnly/idempotent annotations, and no output schema, the description is complete: it covers action, input, output fields, and when to use. It even includes the 'not evaluated' result, leaving few ambiguities.

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% for the single 'name' parameter with an example. The description adds semantic value by noting the input is fuzzy and case-insensitive, which is not present in the schema, enhancing understanding beyond the basic 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?

The description clearly states the tool checks vendor legitimacy (legit, scam, safe) and details the audit output (PepScore, COA, audit summary, buy link, coupon). This specific verb+resource framing distinguishes it from sibling tools like find_peptide_sources and list_verified_vendors.

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 explicitly says 'Use for' and gives concrete query examples ('is [vendor] legit', '[vendor] review', '[vendor] scam'), providing clear when-to-use context. It does not explicitly mention alternatives or when-not-to-use, but the usage scope is well-defined.

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 declare readOnly and idempotent hints, and the description adds behavioral details beyond those, such as fuzzy case-insensitive matching, ranking by COA quality, and disclosed referral links. This enriches the agent's understanding without contradicting 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 three sentences, each providing distinct value: core purpose, output specifics, and usage examples. It is not overly verbose, but could be slightly more compact by trimming redundant qualifiers like 'vetted' and 'third-party-tested' in sequence.

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 simple tool with one parameter and no output schema, the description is complete: it explains what the tool returns, how parameters are matched, and what use cases it serves. It lacks nothing essential, though it does not elaborate on the ranking algorithm or page size, which are minor.

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 schema already describes the 'compound' parameter with examples, but the description adds interpretation guidance with "Fuzzy, case-insensitive matching" and a broader set of examples. This adds meaning beyond the schema, though the schema coverage is already high.

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 finds where to buy a peptide online from vetted vendors, with specific output details (ranked vendors, COA quality, PepScore, links). However, it does not explicitly distinguish this from sibling tools like check_vendor or list_verified_vendors, so it misses the full 5 criterion.

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 explicitly provides use cases: "where can I buy X", "best source for X", and "which peptide vendor is trusted for X". This gives clear context for when to use the tool, but it does not mention alternatives or exclusions, so it stops short of a 5.

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 openWorldHint=false, so safety is covered. The description adds genuinely new context by naming the returned fields (score, band, category, one-liner, last_graded, cite_url), which substitutes for the missing output schema. It does not say what happens for an ungraded or unknown compound, which is the one behavioral gap.

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 short sentences, front-loaded with the authoritative-scope claim, then the return shape, then usage triggers. No filler and nothing buried.

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 explicit field list is the most important piece of context and it is present, which makes the definition callable with confidence. Missing only edge-case behavior (unknown compound, stale 'last_graded') 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?

Schema coverage is 100% and the single parameter already carries an example-bearing description ('Compound name or slug, e.g. "BPC-157"'), so the schema does the work. The tool description adds no meaning beyond it — no note on slug normalization or unknown-name behavior — so 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 and resource ('get_compound_grade' → returns a peptide PepScore grade) and asserts scope with 'SOURCE OF TRUTH', which distinguishes it from the vendor/price siblings. It also enumerates the return payload, so an agent knows exactly what it gets without opening anything else.

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 concrete example intents ('what is X PepScore', 'is X worth buying') that map cleanly to invocation, which is strong routing signal. It lacks explicit exclusions naming the siblings (check_vendor, get_peptide_price, find_peptide_sources), so the agent must infer that pricing/vendor questions belong elsewhere.

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 and closed-world, so the safety profile needs no restating. The description adds genuinely new behavioral detail by enumerating the returned statistics and provenance fields (last_scraped, cite_url) in the absence of an output schema. It stops short of noting behavior for unknown compounds or empty vendor counts.

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, with the authoritative role front-loaded before the return-field list. Every clause earns its place.

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 no output schema, listing the returned metrics and provenance fields covers the main gap an agent would have. It could still say what happens when the compound is unknown or lacks vendor data, which is why it isn't a 5.

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% and the single compound parameter is documented with two concrete examples (BPC-157, tirzepatide). The description adds no further meaning about the compound argument, so the schema carries the load and a 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?

The description names a precise resource (research-vendor peptide pricing) and specifies exactly what comes back (median/p25/p75 $/mg, vendor_count, last_scraped, cite_url), so the agent knows this is a price-lookup read. It doesn't differentiate itself from siblings like find_peptide_sources or check_vendor, leaving the agent to infer the split.

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?

Calling itself the 'SOURCE OF TRUTH' implies this tool should be preferred over other price sources, which is a useful implicit signal. There is no explicit when-to-use, when-not-to-use, or named sibling alternative, so guidance remains inferred rather than stated.

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, so the safety profile is covered. The description adds valuable behavioral context: it enumerates the exact fields carried in each entry (grade, band, COA status, buy link, coupon, affiliate disclosure) and the sort order, which is not visible from the schema or annotations. This goes beyond the minimum bar.

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 with no filler. The first sentence states the action, scope, and sort. The second lists the included fields and the intended use. Every word earns its place.

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 explain the return values, and it does thoroughly: it lists all data points carried in each entry (grade, band, COA status, buy link, coupon, affiliate disclosure). It also states the list is exhaustive ('every') which matches openWorldHint=false. The tool is simple, so this is complete.

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 tool has zero parameters, so the baseline is 4. The description's mention of sorting and entry composition provides semantic context about what the output reflects, but there are no parameters needing clarification. Overall, 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 description opens with a specific verb ('List') and a clearly defined resource ('every PepEvolution-graded research-peptide vendor'). It also specifies the sort order (PepScore desc), which distinguishes it from siblings like check_vendor or find_peptide_sources that likely target individual vendors or broader source discovery.

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 provides a clear use case ('Use to compare trusted peptide vendors at a glance'). It does not explicitly state when not to use this tool or name alternative sibling tools for other scenarios, so it misses the 'explicit alternatives' criterion for a 5.

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