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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds meaningful behavior: inbound-only operation, exclusion of the agent's own comments, and the 50-item limit cap. It omits pagination/truncation behavior when limit is hit, which keeps it from 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?

One dense paragraph, front-loaded with the core action before the scope and parameter mechanics. Every sentence carries information, though the scope enumeration and polling advice make it longer than strictly minimal.

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?

There is no output schema, so the description carries the burden of explaining return semantics and does so partially by referencing polledAt for advancing the poll. It would be stronger if it named the returned fields, but for a 3-param read-only polling tool it is adequately 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 coverage is 100% (baseline 3), but the description goes beyond the schema by motivating each scope enum value and spelling out the incremental-poll pattern for includeCommentsSince. This adds real decision value over the raw field descriptions.

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 ('Poll for Issues tied to your work plus NEW human comments on them') and immediately scopes it to agent-filed/owned issues, which cleanly separates it from the broad list_issues and per-issue get_issue siblings. An agent can tell what it returns 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?

Explicitly prescribes the loop usage ('Use this in your loop to react to feedback on an Issue you filed') and gives per-scope when-to-use guidance, including the fresh-run case for 'reported_by_me'. It also explains why it exists (MCP is inbound-only, a human can't call your session back), leaving nothing to inference.

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