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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the per-action return shape: list returns all folders with their agentIDs, get returns one folder. That is genuine behavioral detail beyond the annotations, though it says nothing about volume, pagination, or how the 'mode' truncation affects these responses.

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?

Two sentences, front-loaded with the resource definition before the action enumeration. No filler, no restatement of the title, and the parenthetical gloss on 'agent folders' earns its place by preventing confusion with sibling folder concepts.

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 no output schema, the description compensates by sketching what each action returns, and annotations carry the safety semantics. The main residual gap is scale: nothing indicates whether 'list' can return hundreds of folders or how 'mode' interacts with these responses, which an agent planning a lookup would want to know.

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 75% and the schema already documents mode, name ('exact folder name, when the id is unknown') and folderId ('For get'). The description only binds action values to their parameters, adding marginal meaning over the schema rather than explaining edge cases such as name collisions or what happens when both folderId and name are supplied.

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?

States a specific verb and resource ('Read the agent folders of the workspace') and immediately disambiguates the domain concept ('the folders that group agents on the dashboard'), which matters in a toolset full of other folder-like objects. It then enumerates the two supported actions and what each yields, so the agent can distinguish this from folders_write without opening the 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?

The action list ('list' vs 'get') plus the note that 'get' works by folderId or exact name gives clear selection context, and 'when the id is unknown' tells the agent when to prefer the name path. It stops short of explicitly contrasting with folders_write or stating that this tool is the read-only counterpart, so it is clear but not fully routing-aware.

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