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

The readOnlyHint=true annotation already covers the safety profile, so the bar is lower. The description adds some useful context — the result contains identifiers and Swiss UIDs — but discloses nothing about pagination behavior, sorting, or whether the list is exhaustive. It does not contradict the read-only annotation, and the added context is modest rather than rich.

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 brief and front-loaded with the core verb+resource, and it packs purpose, output shape, and use case into one sentence. However, the trailing 'norm.' is a confusing artifact that should have been removed — every token should earn its place, and this one detracts from an otherwise tight definition.

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 read-only list tool with five optional parameters and no output schema, the description covers the essentials: what is listed, what the output contains (identifier and Swiss UID), and the motivating use case. Pagination behavior and the lang parameter are not addressed, but they are minor for a tool of this complexity and partly inferable from the schema.

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 60%, leaving lang and page entirely undocumented in both schema and description. The description adds purpose-level context that indirectly explains why one would pass an identifier ('find a publisher's code for a filter'), and the schema already documents uid, limit, and identifier well. It does not meaningfully compensate for the lang/page gaps, so a mid-range score is appropriate.

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 opens with a specific verb and resource — 'List the bodies that publish into I14Y' — and names the key output fields (identifier and Swiss UID). The parenthetical German terms ('Herausgeber, Bundesamt, Kanton, UID') clarify what a 'publisher' is, and the use case ('find a publisher's code for a filter') helps distinguish it from sibling list tools like list_datasets or list_catalogs. It loses the top score only because of the stray trailing fragment 'norm.', which reads as a truncated or garbled word.

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 explicitly states when to use the tool: 'use to find a publisher's code for a filter.' This is clear context that an agent can act on, and the tool name plus the use case implicitly separate it from the other i14y.list_* siblings. However, it does not name alternatives or give when-not-to-use guidance, so it stops short of a 5.

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