Evidence-first peptide research: summaries and comparisons from cited dossiers, linked to courses.
Scored across 4 tools
Each tool has a clearly distinct role: listing/resolving peptides, reading one peptide's dossier, comparing peptides, and searching underlying papers/trials. Although search_papers and get_peptide_research both surface evidence, their target resources and query styles are distinct enough that an agent can select correctly.
All four names use snake_case with a verb-first pattern (compare_peptides, get_peptide_research, list_peptides, search_papers). Minor singular/plural variation in the object noun does not break the predictable convention.
Four tools are well-scoped for a focused peptide research reference server. Each tool covers a distinct workflow, and there is no redundant or filler tool.
The read-only research domain is fully covered: list and resolve peptides, retrieve detailed dossier sections, compare multiple peptides, and search papers/trials behind the dossiers. No obvious lifecycle or lookup operation is missing for this server's purpose.
Put the research summaries of two or three peptides side by side, each with numbered sources and its course link, for questions like "BPC-157 vs TB-500" or "semaglutide vs tirzepatide".
| Name | Required | Description | Default |
|---|---|---|---|
| peptides | Yes | Two or three peptide ids or names. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds useful behavioral context the annotations don't: the response contains numbered sources and a course link per peptide, which matters because there is no output schema.
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 sentence that front-loads the operation, then the output shape, then concrete examples. No redundant or filler text.
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, the description does enough: it explains what is returned (summaries, numbered sources, course link) and when to reach for it. Minor gaps remain around invalid/unknown peptide handling and result ordering.
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 already documents 'Two or three peptide ids or names' with minItems 2 / maxItems 3. The description's 'two or three peptides' merely restates the schema bounds and adds no format or resolution guidance (e.g. what happens with an unknown id). 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+resource ('put the research summaries of two or three peptides side by side') and clearly implies the singular sibling get_peptide_research is not the right call. An agent can tell this apart from list_peptides and get_peptide_research without opening any 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?
Concrete trigger examples ('BPC-157 vs TB-500', 'semaglutide vs tirzepatide') make the use case unambiguous. It doesn't explicitly state when not to use it or name the sibling to fall back on for single-peptide lookups, 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.
Get the evidence on one peptide from its Peptides Academy research dossier, with verbatim quotes from the studies and numbered sources. Without a section it returns the summary and the list of sections; pass a section (for example "human record", "regulatory status", "safety", "mechanism") to read that part in full.
| Name | Required | Description | Default |
|---|---|---|---|
| peptide | Yes | Peptide id or any of its names, for example "bpc157", "semaglutide", "Wegovy" or "GHK-Cu". | |
| section | No | Optional section id or topic from the section list. |
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. The description adds real behavior the annotations don't: the default response shape when no section is supplied (summary + section list) and the fact that content includes verbatim study quotes and numbered sources. No pagination or size limits are disclosed.
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 the core action and return content, then the parameter-mode distinction. Nothing is redundant with the schema or annotations.
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 two-parameter read tool with full schema coverage and rich annotations, the description supplies everything an agent needs: what the payload contains, both calling modes, and how to discover valid section ids. No output schema exists, and the description adequately characterizes return contents instead.
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 naming concrete section values ('human record', 'regulatory status', 'safety', 'mechanism') and explaining that the section list comes from a section-less call — a discovery mechanism the schema only hints at.
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 the evidence on ONE peptide from a research dossier, including verbatim quotes and numbered sources. The singular 'one peptide' plus 'research dossier' distinguishes it implicitly from list_peptides and compare_peptides, which operate on sets.
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 describes the two calling modes: omit section to get the summary plus section list, or pass a section to read that part in full. It does not, however, route the agent toward or away from the sibling tools (list_peptides for discovery, compare_peptides for multi-peptide work).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the peptides Peptides Academy covers, or find the ones matching a name, brand name, code name or topic (for example "Ozempic", "BPC-157", "sleep", "GLP-1"). Returns each peptide id, its names, a one-line summary and its course link. Use it to resolve a peptide id before get_peptide_research.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Optional name or topic to filter by. Leave empty to list all. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so safety needs no restating. The description adds real value by describing the return payload (id, names, one-line summary, course link) and by implying fuzzy multi-field matching. It omits result-set size limits or 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?
Two sentences: the first defines scope and filter modes, the second states the return shape, with the primary use case last. No filler, and the examples earn their space by pinning down match semantics.
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 a single fully documented parameter and no output schema, the description carries the return-value burden itself and does so explicitly. Nothing needed to call this correctly is missing.
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. The description still adds meaning beyond 'Optional name or topic': it clarifies that matching covers brand names, code names and topics, and gives concrete example queries ('Ozempic', 'GLP-1', 'sleep'), which is exactly the disambiguation an agent needs.
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?
Specific verb 'List' plus the exact resource ('the peptides Peptides Academy covers'), and it explicitly enumerates the filter dimensions (name, brand name, code name, topic). An agent can distinguish it from compare_peptides and get_peptide_research without opening any 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?
'Use it to resolve a peptide id before get_peptide_research' gives a concrete calling context and downstream hand-off. It does not state when not to use it or mention compare_peptides, so routing against the sibling list is left partly implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the research papers and trial registrations behind the Peptides Academy dossiers by topic, peptide, author or journal, for questions like "what studies looked at BPC-157 and tendon healing" or "semaglutide cardiovascular outcomes". Each hit gives the citation, DOI, PubMed or ClinicalTrials.gov link, the courses whose research uses it, and what our dossier says about it with short verbatim quotes, numbered as sources. It never returns full texts or abstracts.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many papers to return, 1 to 10. Default 5. | |
| query | Yes | Topic, finding, author or journal to search for, for example "BPC-157 tendon" or "semaglutide cardiovascular". | |
| peptide | No | Optional peptide id or name to limit results to papers behind that course, for example "bpc157" or "Ozempic". |
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 genuinely new behavioral context: what each hit contains (citation, DOI, PubMed/ClinicalTrials.gov link, using courses, dossier commentary with verbatim quotes numbered as sources) and an explicit negative scope (never returns full texts or abstracts). It omits result ordering/relevance behavior, keeping 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?
Three sentences, front-loaded with purpose, then return shape, then negative scope. No filler and each sentence contributes distinct 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?
With no output schema, the description carries the full burden of describing return values, and it does so concretely (citation, DOI, external links, course attribution, quoted dossier text). The negative statement about full texts/abstracts preempts a likely agent misexpectation.
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%, so all three parameters are already documented with examples. The description echoes the query dimensions (topic, peptide, author, journal) but says nothing about the limit parameter or how the peptide filter interacts with query, adding little beyond the schema. 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 (search research papers and trial registrations) plus the corpus it covers (Peptides Academy dossiers) and the dimensions searchable (topic, peptide, author, journal). It does not distinguish itself from the sibling get_peptide_research, which sounds like overlapping territory, so it falls short of 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?
Two concrete example questions ("what studies looked at BPC-157 and tendon healing", "semaglutide cardiovascular outcomes") give clear context for when this tool is the right call. There is no explicit exclusion or pointer to get_peptide_research for the lookup-by-peptide case, so it stops at 4.
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.
search_paperscompare_peptidesget_peptide_researchlist_peptidesPeptide research profiles, evidence by tier, comparisons and educational content. No dosing.
Peptide reference and exact math: reconstitution units, blends, supply, dose ranges by origin.
Evidence-rated German database of supplements, peptides and longevity methods, plus podcast.
Live research peptide prices, price history, vendor trust records and a reconstitution calculator.
Add one secure layer between your agents and this server.
