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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description goes well beyond them: matches are point-in-time snapshots, the three status values are defined (rebooked, open_at_last_scan, unverified), and it warns that status_as_of is a look time rather than a live check. It even advises against calling a stored opening bookable because cancellations get rebooked within minutes. This is exactly the extra behavioral context the annotations cannot carry.

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?

Front-loads the definition and the polling rationale, then moves to status semantics and finally the site-locating caveat. It is longer than typical, but the length is dense and largely justified by domain-specific status rules; only minor trimming would be possible.

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 values need not be re-explained, and the description still covers the cursor pattern, status interpretation, and timestamp caveats that an agent needs to use results correctly. Nothing material is missing for a read-only list tool.

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%, so baseline is 3, but the description adds real meaning for `since`: it is the cursor from a previous call, and omitting it returns recent matches that may already be seen/acted on. That clarifies the trade-off the schema only names. `alert_id` and `limit` are left 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?

States a specific verb and resource ('Openings the user's alerts have found') plus ordering ('newest first'), and frames it as the check-in mechanism for alerts an agent created. An agent can distinguish it from get_alert or list_my_alerts immediately.

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 explains why to call it (MCP cannot push, so polling is the only way to learn about matches), how to use it incrementally via `since` cursor, and what happens if you omit it. It also names alternatives for a related need (get_zone_map and list_zone_sites for locating sites), so routing is unambiguous.

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