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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds genuinely new behavior: it is non-blocking, 'wakes nothing', is safe to poll, is not metered, and — critically — that enqueued/processing are current-state counts rather than lifetime totals while completed counts finished effects. That counter semantics note prevents a real misreading of the output and is not in any structured field.

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 return contents, then the count semantics, then routing to alternatives — a sensible order with little waste. Minor redundancy in restating 'Read-only' when readOnlyHint already declares it, though 'not metered' is new information.

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 shape needn't be restated, yet the description still resolves the ambiguity an agent would hit — what each count means and whether polling is safe. For a single-parameter read tool with full annotation coverage, nothing needed is missing.

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 the single workspace_tag parameter is fully documented in the schema as the active workspace id. The description adds nothing about the parameter, so the baseline 3 applies — the schema does all the work here.

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 ('Returns a non-blocking summary of the workspace's processing') and enumerates the payload: counts by public domain and state, unresolved failures, and inspectable public Tasks. It distinguishes itself from tasks_get and wait_for_workspace_idle by explicitly routing those use cases elsewhere.

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?

Gives explicit alternatives with the conditions that select them: 'For one public Task use tasks_get or tasks/get; for a bounded workspace barrier use wait_for_workspace_idle.' It also tells the agent this is safe to poll, which is direct usage guidance.

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