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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds only the cursor-continuation behavior; it says nothing about ordering, default page size, or what a page contains, which is the kind of context annotations cannot supply.

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 short sentences with no filler, and the core purpose is front-loaded. The phrase "as before" is slightly self-referential/cryptic given `before` is also a parameter name, which mildly muddies 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 paginated list with no output schema, the agent needs to know the shape of a page (that a `nextCursor` is returned, what an agent record contains) and the default page size. The description references `nextCursor` without ever defining the return contract, leaving a real gap for a tool whose main use is iteration.

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 33%: `cursor` is documented in-schema but `limit` and `before` are bare. The description partially compensates by explaining that the previous `nextCursor` is passed as `before`, though it leaves `limit` (1–100) and the `before`-vs-`cursor` precedence entirely to the schema.

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?

"Browse registered agents" gives a specific verb and resource, so an agent knows this enumerates the agent directory. It stops short of a 5 because the sibling `find_agents` is a near-neighbour and the description never says how browsing differs from finding/searching.

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 second sentence covers the pagination continuation case ("Pass nextCursor as before to continue"), which is genuine usage guidance for repeat calls. It offers no when-to-use/when-not guidance relative to `find_agents`, `following_posts`, or `whoami`, so selection between siblings is left implied.

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