Sourced studies of what a town was like in a given decade: work, faith, law, money, news.
Scored across 3 tools
Each tool has a clearly distinct purpose: about_yore explains the service and methodology, search_places discovers available studies, and get_place retrieves a specific study. There is no overlap that would cause an agent to misselect a tool.
get_place and search_places follow a consistent verb_noun pattern, while about_yore uses a preposition_noun form. All names use snake_case and are readable, so the deviation is minor.
Three tools are well-scoped for a read-only reference service: one for background, one for discovery, and one for retrieval. Each tool earns its place without bloat or obvious under-provisioning.
The set covers the full lifecycle of a read-only place-study service: understanding the source and certainty labels, searching the catalog, and retrieving a full study. No create/update/delete operations are needed for this domain, and there are no obvious dead ends.
What Yore is, how its place studies are researched and from what kinds of source, what its certainty labels mean, what the studies do not cover, and how to cite them.
| 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 and locality are covered by structured data. The description adds genuine scope context by disclosing that the studies have limits ('what the studies do not cover'), which matters for downstream trust in the data. It does not mention whether the content is static or cached, but that is a minor omission against annotation coverage.
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 that lists the covered topics without filler. It is slightly list-heavy and could have led with a verb ('Explains what Yore is...'), but every clause corresponds to a real content area.
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 zero parameters and no output schema, the description carries the full burden of describing the return content, and its topic enumeration does that adequately. An agent knows what it will get back and can decide whether it needs this background before interpreting place studies.
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 takes zero parameters, so per the rubric the baseline is 4. There is nothing for the description to disambiguate, and it does not waste words on non-existent arguments.
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 enumerates what the tool returns: Yore's identity, research methodology and source types, certainty labels, coverage gaps, and citation guidance. It reads as a self-description/documentation resource rather than a tautology. It stops short of naming its siblings or stating an explicit verb like 'explains', but the topic list makes the purpose unambiguous.
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: an agent can infer this is the orientation/background call, and the mention of certainty labels suggests checking it before interpreting study data. However, there is no explicit when-to-use trigger, no prerequisites, and no routing versus get_place or search_places.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The full study of one place in one decade as Markdown: a look around, work, faith, law and power, money, what people feared, a year-by-year list, what each source says, and the numbered sources with links.
| Name | Required | Description | Default |
|---|---|---|---|
| place | Yes | A place name (e.g. "Mauch Chunk"), or the place id a search result gives (e.g. "mauch-chunk-carbon-county-pennsylvania"). | |
| decade | Yes | The decade as its first year, e.g. 1820. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. Because there is no output schema, the description carries the return-shape burden and does so well by enumerating the Markdown sections and noting that sources include links. It omits size/length expectations but is otherwise solid.
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 that names the subject and format first, then lists the contents. Every clause is content-bearing, though the long content list is dense and could be trimmed without loss.
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 explains the return structure, and read-only behavior is covered by annotations. The main gap is the absence of routing guidance relative to the sibling search/about tools.
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 both parameters (place, decade) are already documented with examples and format. The description adds no parameter-level meaning beyond what the schema provides, which is the baseline 3 case.
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 scoped precisely: 'the full study of one place in one decade as Markdown.' The enumerated contents (work, faith, law, year-by-year list, sources) make clear what 'full study' means. It does not name or differentiate against siblings like search_places or about_yore, so it lands at 4 rather than 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?
No when-to-use or when-not-to-use guidance is offered. The agent is not told to call search_places first to obtain a place id, nor how this differs from about_yore. Usage must be inferred from the title and schema alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find the places Yore has researched: each is a sourced study of what one town, county or city was like in one decade (work, faith, law, money, dangers, news, year by year). Search by any words from the place's name or region ("Wilkes-Barre", "Luzerne Pennsylvania", "Essex England"), optionally in one decade. With no query it lists everything.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | At most this many (default 25, most 100). | |
| query | No | Words from the place name or region. Leave out to list all. | |
| decade | No | A decade as its first year, e.g. 1880. |
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 that a search with no query behaves as a full listing, which is genuinely useful behavioral information, but it says nothing about result ordering, pagination beyond the limit param, or matching behavior (fuzzy vs exact).
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 the purpose, then search mechanics, then the no-query default. The parenthetical listing of study subjects (work, faith, law, money, dangers, news) is slightly ornamental but helps convey the resource's nature without much cost.
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, and the description does characterize what a result is (a sourced study of a place in one decade), which compensates. With annotations covering safety and the schema covering parameters, the definition is complete enough to call correctly, though result ordering/count semantics are unstated.
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 the baseline is 3, but the description goes further by giving concrete query examples ('Wilkes-Barre', 'Luzerne Pennsylvania', 'Essex England') that clarify the multi-word/region matching style, and by tying the decade parameter to the query ('optionally in one decade').
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 (Find/Search) and resource (places = sourced decade studies of a town/county/city), and even elaborates what a 'place' record contains. It doesn't explicitly contrast itself with the get_place sibling (singular lookup) or about_yore, so it stops short of full sibling differentiation.
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?
It explains the no-query fallback ('with no query it lists everything') and the optional decade filter, implying when the tool applies, but never says when to use this instead of get_place or about_yore. Usage is inferable rather than explicit.
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.
about_yoreget_placesearch_placesSourced history by year: events, world leaders, prices and No. 1 songs, each with its source.
Sourced facts on locally owned places, records, events and neighborhoods in Milwaukee County.
Search LOC digital collections, Chronicling America newspapers (full OCR), and LC Subject Headings.
Read-only U.S. household-finance research: economic indicators, county scores, ADI and citations.
Add one secure layer between your agents and this server.
