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.