List your collections (Samling)

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

Annotations already declare readOnlyHint=true, and the description reinforces this by stating 'Read-only' and 'never writes'. It adds valuable context beyond annotations: the response exposes `containingCompSedisIds` as an array of ids (not nested objects), enabling a reference-then-resolve workflow, and notes tenant-scoping. It also clarifies that write operations are not exposed here, which is useful behavioral disclosure.

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 three sentences long, with every sentence earning its place. It leads with 'Read-only', explains the key output format, gives a concrete example, and ends with an explicit write-exclusion. No fluff or repetition of schema details.

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?

Given the tool has an output schema, the description does not need to explain return values. It covers the essential context: tenant scoping, read-only nature, the shape of `containingCompSedisIds`, a usage pattern with another tool, and a concrete filter example. This is complete for a list operation with well-documented parameters and output.

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 input schema provides 100% coverage with descriptions and examples for all four parameters (page, sort, pageSize, nameContains). The description does not add new parameter-specific semantics beyond repeating the nameContains example, which is already in the schema. It does provide context on how to use the output with another tool, but that does not directly enhance parameter understanding.

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 states the tool lists collections (Samling), names the exact resource, and distinguishes itself as read-only. It also differentiates from sibling tools by explicitly noting that creating/replacing/deleting a Samling is not exposed here, and references how the output feeds into `fastighetsbenchmark_get_comp_timeseries`.

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 provides clear context for using the tool: it lists YOUR collections, is tenant-scoped, and is read-only. It gives a specific example (`nameContains 'Stockholm offices'`) and advises passing the resulting `containingCompSedisIds` to `get_comp_timeseries` only for needed collections to keep payloads bounded. It does not explicitly contrast with sibling list tools like `list_jamforelseobjekt`, but the scoping and read-only nature make the usage clear.

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