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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context about default-off semantics and the global-over-agent precedence, but 'Jev never grants permission' is cryptic and unexplained, adding little actionable clarity.

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?

Three short sentences, front-loaded with the core read purpose before the behavioral caveats. No filler, though the final sentence about 'Jev' is opaque enough to feel wasted.

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 simple read-only tool with a fully documented single parameter, the description is adequate. However, with no output schema, it does not describe what the returned policy or flags look like, and the permission sentence is too vague to resolve the tool's authorization behavior.

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 description coverage is 100% and the single connection parameter is fully documented in the schema, including the credential's origin and handling rules. The description adds nothing about the parameter, 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 (Read) and resources (private semantic policy, effective feature flags), which is more concrete than the tool name semantic_status. It implicitly distinguishes itself from the write sibling semantic_policy_update, but never names it explicitly.

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 description explains a default state ('Off by default') and a precedence rule ('global flags cap per-agent settings') but gives no guidance on when to call this tool versus semantic_policy_update or the sharing_setting tools. No trigger condition or exclusion is provided.

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