Read-only search and retrieval for Official Translator's published guides.
Scored across 2 tools
The two tools have clearly distinct roles: search finds candidate guides, and fetch retrieves the full text of a specific guide. Their descriptions explicitly explain the sequencing and prevent overlap.
Both names follow a consistent snake_case verb_noun pattern: search_published_guides and fetch_published_guide. The singular/plural distinction aligns naturally with their functions.
Only two tools is thin, but the server appears narrowly scoped to searching and fetching public guides. The pair is coherent, though it sits at the borderline of minimal tool surface.
The search-then-fetch pattern covers the core retrieval workflow for answering from published guides and citing sources. Minor gaps may exist, such as browsing all guides without a query, but agents can work around this via search.
Use this after search_published_guides finds a relevant result. Fetch the full text and FAQ of one published Official Translator guide by its slug so you can answer from the source and cite its URL. Draft articles are never returned.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description's value is what it adds: return payload is full text plus FAQ, and a URL is included for citation. It also discloses a filtering rule (drafts excluded), which is behavior an agent cannot infer from 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?
Two sentences, zero filler, and the usage trigger is front-loaded before the description of what is returned. Every clause contributes either routing or return-value 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 correctly explains what comes back (full text and FAQ, plus a URL to cite) and what is excluded (drafts). The only gap is slug formatting/validation guidance and what happens on an unknown slug, which is minor for a single-parameter read 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 description coverage is 0% for the single 'slug' parameter, so the description must carry the load; it only says 'by its slug', implying the slug originates from a prior search result. It adds useful provenance but no format, length, or error behavior detail beyond the schema's constraints.
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 (fetch) and resource (one published Official Translator guide, full text plus FAQ) and names the scope qualifier 'published'. It clearly contrasts with the sibling search_published_guides, which only finds results rather than returning content.
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 this after search_published_guides finds a relevant result' gives explicit sequencing and points to the alternative tool. 'Draft articles are never returned' adds a negative scope, though there is no explicit statement of when not to call it (e.g., non-guide content).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use this when a user asks about document translation, Apostille, visas, countries, or institutions covered by Official Translator. Search published public guides in Macedonian and English; returns titles, summaries, language, and source URLs. Fetch the most relevant result before answering.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | ||
| language | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds real value on top: results are limited to *published public* guides only, covering Macedonian and English, and it names the fields returned (titles, summaries, language, source URLs). It does not mention ranking behavior or what happens when nothing matches, which is the only notable 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 sentences, all load-bearing: trigger condition first, then scope and return shape, then the follow-up action. No restatement of the tool name or 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?
No output schema exists, and the description compensates by enumerating returned fields and the two supported languages. A mutation-free, three-parameter search tool is well covered; only result-count/empty-result behavior is left 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 0%, so the description must carry the burden. It partially compensates by constraining the query domain (translation, Apostille, visas, countries, institutions) and by implying the language filter via "Macedonian and English," but the `limit` parameter and query format/length expectations are never explained.
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 specific resource (published public guides) plus domain scope (document translation, Apostille, visas, countries, institutions covered by Official Translator). It also previews the return payload, so an agent can tell this apart from fetch_published_guide, which is the retrieval step that follows.
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 explicit trigger conditions ("Use this when a user asks about document translation, Apostille, visas...") and explicitly routes to the sibling workflow step with "Fetch the most relevant result before answering." Both when-to-use and what-to-do-next are stated rather than inferred.
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.
fetch_published_guidesearch_published_guidesRead-only Bicycle Guide registry: published guides, homes, taxonomy, capability spine. No auth.
Read-only Bicycle Guide registry: published guides, homes, taxonomy, capability spine. No auth.
Read-only Bicycle Guide registry: published guides, homes, taxonomy, capability spine. No auth.
Read-only Bicycle Guide registry: published guides, homes, taxonomy, capability spine. No auth.
Add one secure layer between your agents and this server.
