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

Beyond readOnlyHint/destructiveHint (which the "Reads only" note merely confirms), it discloses non-obvious behaviors: long text is truncated in results, drafts are included, results are paged with a total, and locale returns fallback default text plus per-item translation state and translated slug. The key gotcha that search, filters and sort operate on default-language values is exactly the kind of caveat an agent cannot infer from the schema.

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?

Extremely information-dense and front-loaded with the core action, with no filler. The trade-off is a run-on structure where pagination, truncation, and locale behavior are packed into one block, which makes it harder to scan than a short bulleted layout would be.

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 10 parameters, no output schema, and an unfamiliar domain (CMS content with localization), the description supplies what the structured fields cannot: result shape hints (paged, total, truncated text, translation state), default-language scoping rules, and the fallback relationship to get_item. Nothing material for a correct first call is missing.

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 coverage is 70%, and the description compensates by explaining locale semantics — that it must be a non-default language from list_locales on a translatable collection, that missing translations fall back to default text, and that query operations still use default values. It also restates the filter operators and gives the sort example, adding modest value over the already-documented schema fields.

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 concrete verb and resource ("Lists a collection's items") and then enumerates the exact capabilities: search q, status, field filters with the supported operators, sort syntax, pagination, and totals. It also distinguishes itself from the sibling get_item ("Long text is cut: get_item reads one whole"), so an agent can route correctly without opening either schema.

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 states the alternative for full content (get_item) and the prerequisite chain for related inputs (locale "from list_locales", collection "from list_collections", projectId "from list_projects"). It does not explicitly cover when to prefer a different listing strategy, but for a listing tool the routing context is clear enough to act on.

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