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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond them by stating that even the "approvals" section is read-only and cannot perform the approval, preventing a plausible misuse. It says nothing about output shape or pagination, 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?

Two short sentences, both front-loaded: the capability first, the boundary second. No filler, and the restrictive clause immediately follows the enumeration it qualifies.

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 one-parameter, no-output-schema, annotation-covered tool this is close to sufficient, but the agent still cannot tell what each section yields or how "approvals" differs from the ask_human and wait_for_approval siblings. A short per-section gloss would close the remaining gap.

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 0% and the single enum parameter carries five values with no field-level documentation, so the description must compensate. It roughly maps the enum values to resources (agents, activity, plans, usage, approvals), but the correspondence is loose — "human questions" for "approvals", "plan limits" for "plans" — and it never says what each section actually returns.

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?

"Read" plus an enumerated resource list (workspace agents, MCP activity, plan limits, usage, human questions) tells the agent this is a read-only multi-section viewer. The negative clause further pins its identity against siblings like wait_for_approval and ask_human, though the phrase "human questions" does not cleanly map to the enum value "approvals".

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 gives explicit when-not-to-use guidance: it cannot approve agents, answer questions, or manage billing, which steers the agent away from misusing it for mutations. It stops short of naming the correct alternatives (e.g., wait_for_approval or ask_human), so routing is implied rather than prescribed.

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