Search a directory of Latina software engineers, plus communities, programs and job boards for them.
Scored across 4 tools
Each tool has a clearly distinct purpose: get_member retrieves a single member by slug, search_members searches the member directory, list_resource_categories lists category metadata, and search_resources searches resources. There is no overlap that would cause misselection.
All tool names follow a consistent verb_noun snake_case pattern (get_member, list_resource_categories, search_members, search_resources). The singular/plural difference (member vs members) is logical and does not break predictability.
Four tools are well-scoped for a read-only directory of members and resources. Each tool covers a distinct operation, and the count is neither too thin nor excessive for the domain.
The surface covers member retrieval and search, plus resource category listing and resource search. However, there is no direct way to fetch a specific resource by ID/slug, and no tool to list all resources globally without specifying a category, which are notable gaps for a resource directory.
Get one Latina Dev member's public profile by slug, the last part of their profile URL (https://latina.dev/members/).
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Profile slug, e.g. "frances-coronel" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safe-read profile is covered structurally. The description adds that the returned data is a 'public profile,' implying no auth-gated or private data, but it says nothing about what fields are returned or whether the record can be missing.
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 front-loaded sentence with the verb, scope, parameter, and a concrete example. Every clause earns its place and nothing is padded.
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-only lookup with no output schema and annotations covering safety, this is nearly sufficient. The only gap is that with no output schema the agent has no sense of the returned profile shape, though that is a minor omission for a retrieval 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 100%, so the baseline is 3, but the description goes further by defining slug as the last part of the profile URL and providing the example URL pattern. That gives the agent a way to derive the value, which the schema alone 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?
States a specific verb and resource ('Get one Latina Dev member's public profile') with clear singular scope that contrasts with the search_members sibling. It does not explicitly name search_members as the alternative, but the 'one ... by slug' framing makes the distinction inferable.
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 rather than stated: the description explains that slug is the trailing URL segment, which helps an agent invoke it correctly, but never says when to use this lookup versus search_members (e.g., when you already have a slug). No when-not guidance is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the resource categories on latina.dev/resources, such as communities, K-12 and college programs, job boards and conferences, with how many resources each has.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely useful context beyond that: the target domain and the fact that each category is returned with a resource count, which compensates for the absent 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 front-loaded sentence beginning with the verb and resource. The embedded examples earn their place by illustrating what a 'category' is, though they make the sentence a touch long.
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 no-parameter, read-only discovery tool with no output schema, the description adequately conveys what is returned (categories plus counts). Nothing an agent needs to call it 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?
With zero parameters and 100% schema coverage, there is nothing to document; the description correctly avoids inventing parameter semantics. Baseline 4 applies for a no-parameter tool.
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 'List' with a clear resource 'resource categories' scoped to latina.dev/resources, and gives concrete examples (communities, K-12, job boards). It implicitly distinguishes itself from search_resources by dealing in categories rather than individual resources, though it never names a sibling 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?
The description conveys the intended use (browsing available categories) but offers no explicit when-to-use, when-not-to-use, or routing guidance versus search_resources. Usage is only implied by the verb and examples.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the Latina Dev directory of Latina software engineers. Every keyword in query must match the member's name, title and company or school, location, countries of heritage, level, what they are open to or bio. Filters narrow results further. Leave everything empty to list members. Returns public profile fields and the profile URL.
| Name | Required | Description | Default |
|---|---|---|---|
| level | No | Career level | |
| limit | No | Most results to return, 1 to 50 (default 20) | |
| query | No | Keywords, e.g. "Google", "Austin", "frontend", "Stanford" | |
| country | No | Country of heritage | |
| open_to | No | What the member is open to |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the read-only, closed-world safety profile, and the description adds genuinely useful behavior: AND-semantics ('every keyword must match') across a named set of fields, and the fact that only public profile fields plus a profile URL are returned. No pagination or ordering behavior is disclosed, which keeps it from 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?
Four short sentences, all front-loaded with the directory search first, then matching rules, empty-state behavior, and return shape. Minor redundancy in 'Latina Dev directory of Latina software engineers,' but no dead weight.
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 states the return shape (public profile fields + profile URL), and it documents empty-query behavior and matching semantics for a 5-param, 0-required tool. It omits result ordering and how `limit`/truncation interacts with matches, the one remaining 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 coverage is 100%, so the baseline is 3; the description goes beyond it by specifying exactly which member attributes each `query` keyword is matched against (name, title, company/school, location, heritage, level, open-to, bio), which the schema only illustrates with examples. It also clarifies that the other four params act as narrowing filters rather than replacements for the keyword search.
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 (Search) and resource (the Latina Dev directory of Latina software engineers), plus the scope of what is searchable. An agent can distinguish this from get_member (single profile) and search_resources (resources) without opening a 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?
Gives clear operating context: filters narrow results, and leaving everything empty lists members, which tells the agent how to use it as a browse tool as well as a search. It stops short of naming alternatives (e.g. use get_member for one profile), so no explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the communities, student programs, scholarships, job boards, career and leadership groups, conferences, founder support, podcasts, newsletters and reports that Latina Dev lists for Latina software engineers. Every keyword in query must match a resource's name, description or category. Leave it empty to list everything in a category.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Most results to return, 1 to 50 (default 20) | |
| query | No | Keywords, e.g. "mentorship", "scholarship", "podcast", "cybersecurity" | |
| category | No | Category id from list_resource_categories |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes beyond the readOnlyHint/openWorldHint annotations by disclosing the matching rule: every keyword must match name, description or category, which is AND semantics rather than the OR an agent might assume. It does not mention pagination behavior or result ordering, but for a read-only search that is a minor omission.
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, no filler, and the scope statement precedes the usage rule so the reader gets identity first and behavior second. The enumeration is long but each item is a genuinely distinct resource type an agent may need to recognize in results.
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?
No output schema exists, yet the description covers the essential contract: what is searched, what counts as a match, and how to broaden to a full category listing. Return shape and default limit are handled by the schema, so the remaining gap is small.
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, and the description earns above that by clarifying that query keywords are conjunctive and that an empty query combined with a category lists everything. It adds real semantics beyond the schema's terse 'Keywords, e.g. ...' phrasing.
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 ('Search') plus an explicit inventory of the resource types covered (communities, scholarships, job boards, conferences, podcasts, newsletters, reports). This clearly separates it from siblings like search_members and list_resource_categories, which operate on different entities.
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?
States clear usage context ('Leave it empty to list everything in a category') and implies the category parameter should come from list_resource_categories. It does not explicitly say when to prefer this over search_members, but the domain scope is narrow enough that disambiguation is easy.
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.
get_memberlist_resource_categoriessearch_memberssearch_resourcesRecruiter-scoped search across Latin America's largest tech talent pool. OAuth-authenticated.
Search DevRel tools, communities, jobs, events, CFPs, and guides from devrel.directory.
Hiring developers? Find and source software engineers by what they build on GitHub.
Add one secure layer between your agents and this server.
