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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds genuinely new behavioral facts: the feed is public, ordered oldest first, and events carry ids, statuses and counts only (i.e. no payload bodies). It does not mention retention limits or rate behavior, so not a 5.

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 scope, then the continuation and filtering instructions. Every clause carries information and nothing is redundant padding.

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 full schema coverage, the description need not explain return values, and it still usefully notes the event payload shape. The main gap is first-use guidance: nothing says whether the feed is the right starting point versus the issue-status or history siblings.

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 100% and the parameter descriptions already explain all three fields, including the after-cursor continuation semantics. The description restates the after/next_cursor loop and the server_id filter without adding format, bounds, or edge-case detail beyond the schema, so the baseline 3 applies.

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 public change feed of the MCP directory") and enumerates the event types covered (listing updates/removals plus issue lifecycle transitions). This is clearly distinguishable from siblings like koskamo_get_mcp_issue_status or koskamo_list_revisions, which fetch single records rather than a feed.

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?

Gives operational usage for pagination ("Pass after with the previous next_cursor to continue") and optional filtering by server_id, which tells the agent how to drive the tool. It never says when to prefer this feed over koskamo_get_history, koskamo_get_mcp_issue_status, or koskamo_list_revisions, so the selection guidance is only implied.

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