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

Annotations already cover readOnly/idempotent/non-destructive, but the description adds real value beyond them: the auth scope ('works with mcp:read tokens') and the conditional omission semantics (freshness and regionalIssue omitted when empty, incidents null when none). It stops short of covering cost/latency or how freshness is computed, 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?

Front-loaded with the purpose, then the routing rule, then output shape — no filler sentences. Slightly docked because the field-by-field return enumeration partially duplicates an output schema that already exists, even if the omission/null semantics within it are useful.

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 two-parameter read-only diagnostic aggregator with an output schema, this covers purpose, alternative, auth requirements, and edge-case shape of the response. An agent has everything needed to select and call it correctly and to interpret sparse results.

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 both parameters carry their own descriptions (identifier as UID/slug, recentResultsLimit as 1-20 default 5), so the schema does the work. The description only echoes 'recent raw results across regions' and adds no syntax or edge-case detail beyond it — baseline 3.

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 (diagnose/return) and resource (a single check's current state) and enumerates exactly what is bundled: status, recent regional results, active incident, last resolved incident. This makes it trivially distinguishable from list_results, list_incidents, and get_check without opening any 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 says to use it 'instead of chaining list_results + list_incidents' and names the triggering situation ('a human asks what's wrong with check X?'). The alternative and the condition that selects this tool are both stated outright.

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