Muhu island dialect of Estonian — dictionary and RAG

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds genuine context by naming what the record contains (examples, source, verification status), but says nothing about error behavior for unknown ids or access scope.

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?

One compact sentence with no filler, and the resource and returned content are front-loaded. It is efficient but terse enough that it omits routing and parameter 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 usefully enumerates return contents (examples, source, verification status), and annotations cover safety. However, for a lookup-by-identifier tool it leaves the meaning and provenance of the required id unexplained, which is a meaningful 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 description coverage is 0%: the single required 'id' parameter is only typed as an integer with minimum 1, and the description never mentions it. With one required parameter and zero schema documentation, the description should explain what the id identifies and how to obtain it, which it 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?

The verb 'Loe' (read) plus the resource 'muhu keele avalikku kirjet' (public record of the Muhu language) states a specific action and target. It does not name or contrast with the siblings search_muhu or list_muhu_sources, so differentiation is left to inference.

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 statement of when to use this tool rather than search_muhu or list_muhu_sources, and no prerequisite guidance such as where a valid id comes from. Usage is only implied by the 'public record' framing.

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 that the tool is read-only, idempotent, non-destructive and limited to a closed world. The description adds real behavioral value beyond them: it states what each record returns (references, availability, licence, quality), how sources are classified (human dialect text vs ASR/OCR text vs standard-language background), and that external full texts are not imported into the local corpus. That last sentence is important context for deciding whether this tool is enough.

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 sentences, front-loaded with the resource and scope. The enumeration of source names is dense but earns its place, because it defines scope. The classification sentence and the corpus-import caveat are each doing real work.

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, no parameters and rich annotations, the description covers what the agent needs: what is listed, what fields come back, how to interpret the source types, and the limitation that full texts are not local. The remaining gap is explicit guidance on choosing this tool over its two siblings. The description is also written in Estonian while the tool names are English, which may cost a non-Estonian agent a little parsing effort.

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 no parameters, so the baseline is 4. Schema coverage is 100% and additionalProperties is false, and the description correctly does not waste words on nonexistent inputs. There is nothing further it could add on parameter semantics.

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 states a concrete verb and resource: listing all Muhu dialect text, book and audio source collections for Estonian. It enumerates the specific source collections (Saarte Hääl, ERR, Muhulane, EKI, Pärandikool), which makes the tool's scope unmistakable. It does not explicitly name the siblings search_muhu and get_muhu_entry, so the differentiation must be inferred from the resource name 'sources'.

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 only implied: this is the tool for enumerating source collections. There is no statement of when to prefer it over search_muhu (content search) or get_muhu_entry (single entry lookup), and no prerequisites or exclusions are given. The mention of licence and availability hints at provenance use cases, but nothing explicitly routes the agent.

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, non-destructive, and closed-world behavior. The description adds meaningful context that results may include unverified records and should be source-cited, but it does not discuss pagination, rate limits, or other operational 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?

The description is front-loaded and reasonably short, but the second sentence repeats the dialect/island/Estonia information already in the first. The bilingual duplication adds little beyond language accessibility.

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 search tool with no output schema, the description gives the domain and a useful result-handling caveat about sources and unverified entries. It remains incomplete because it does not explain the available parameters or expected return structure.

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 explain q, limit, and direction. It only hints at bilingual searching via 'Kasuta nii muhu kui eesti teksti' and does not explain the limit or direction parameters, leaving most parameter meaning to inference from names.

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 uses a specific verb ('Otsi' / search) and names the resource precisely: Muhu dialect words, expressions, and examples. It clearly distinguishes the domain from generic search, but it does not explicitly contrast itself with siblings like get_muhu_entry or list_muhu_sources.

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 gives useful usage context: use both Muhu and Estonian text, cite sources, and distinguish unverified entries. However, it never states when to use this tool versus get_muhu_entry or list_muhu_sources, leaving alternative selection implicit.

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