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

Annotations already declare read-only, idempotent, non-destructive behavior, yet the description adds substantial non-obvious context beyond them: the bearer-token auth requirement, public-vs-private readability and operator administration, that 'Tokens and signed URLs are never returned in listings', name-based sort order, and that 'concurrent changes can shift pages'. These are exactly the operational facts an agent cannot infer from the structured fields.

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 definition is poorly front-loaded, opening with two sentences about illustrative path values and placeholder URLs instead of what the tool does. A large fraction of the text is download-flow guidance ('request its download link through POST /api/v1/storage/downloads') that belongs to a different operation, so a listing tool's description is diluted by tangential retrieval advice.

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?

An output schema exists, so return-value documentation is not required, and the description still usefully notes that folder entries use kind 'folder' and may have null metadata. Auth, pagination, namespace scoping, path formatting, and visibility rules are all covered, leaving only rate limits, the 'limit' parameter, and the exact listing fields unspecified.

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 0%, so the description bears the load, and it does so for three of four parameters: folder (relative to the agent namespace, '/'-separated, no leading slash/backslash/percent-encoding/dot traversal, one folder at a time, defaults to root), bucket (public vs private accessibility), and cursor (must be followed with the same bucket and folder). It is silent on 'limit', and it refers to 'next_cursor' while the schema names the parameter 'cursor'.

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 verb (list) and resource (storage files/folders within a bucket) are identifiable, and the description distinguishes the listing path from retrieval ('request its download link through POST /api/v1/storage/downloads... do not append the filename to the website origin') and from saving. However, the opening sentences are meta-commentary about example paths rather than a statement of purpose, so the actual function emerges late ('List one folder at a time; folder defaults to the root').

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 implied rather than stated: 'List one folder at a time; folder defaults to the root' and 'Follow next_cursor with the same bucket and folder' tell the agent how to page through listings. It also routes retrieval elsewhere (POST /api/v1/storage/downloads) rather than through this tool, but there is no explicit 'use this tool when you want to browse X instead of Y' framing or named sibling alternative.

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