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

Annotations already establish readOnly, idempotent, non-destructive and closed-world, so the safety bar is covered. The description adds genuinely new behavior: results come newest first, the slug mode expands from a windowed list into every public change since the product's first drive, each entry carries its source, and no key is required. It does not mention result limits or pagination, which would have pushed this higher.

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 core listing behavior and ordering are front-loaded, and the closing sentence bundles permission model and narrowing options efficiently with no wasted paragraphs. Some phrasing is dense and mildly convoluted ("products whose agent level moved between two drives"), and the long parenthetical stacks several return fields that the output schema likely already covers.

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 an output schema present and annotations carrying the safety profile, the description needs only mode selection and scoping, both of which it supplies, plus the dual-mode result-shape change that an agent would otherwise misjudge before calling. Only the omission of result volume/pagination behavior keeps it from being fully complete.

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 100%, so the schema already documents days (1-31, default 7), slug provenance (from search_tools) and category provenance (from list_categories). The description only restates these as "narrow it with days, category or slug" and reinforces the slug mode's expanded scope, adding little syntax or behavioral nuance beyond the structured fields. Baseline 3 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?

"List what changed in the directory lately" gives a concrete verb and resource, then immediately names the payload (agent-level moves, date, cause, current level) and the ordering (newest first). It also distinguishes the two modes (directory-wide vs. single-product via slug) and names get_provider as the sibling for the full drive result, so an agent can separate it from compare_providers or get_agent_surfaces without opening a 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?

Explicitly routes the agent: send a slug for a full dated history of one product, but use get_provider when you want the full drive result; narrow by days, category or slug otherwise. The one gap is the absence of an explicit when-not-to-use case (e.g. how this differs from list_best_providers or compare_providers for ranking questions), which is left to inference.

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