parallel_learning_status

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

With no annotations, the description carries the full burden. It does disclose one real behavioral trait — the data is cached, so results may be stale and no browser interaction occurs. But it omits whether the cache can be refreshed, how old the data may be, whether this requires an active account session, and what the response shape is. For a status tool with zero annotation coverage, that is thin.

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?

A single short sentence with no filler, and the primary scope distinction is front-loaded. But the terseness crosses into under-specification — 'never browser polling' is a dangling fragment whose meaning depends on context the reader doesn't have.

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?

There is no output schema, no annotations, and 0% parameter documentation, so the description is the only source of truth — and it never describes what status fields come back or how they differ between the two modes. An agent can guess it is a read, but cannot predict the result well enough to plan around it.

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%, so the description must compensate. It implicitly maps account_id (present = account-specific, absent = all-account summary) and hints at detail via 'compact', but it never explains what detail=true actually changes or what the default behavior is. Partial compensation only.

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?

The description names the resource (parallel learning status) and states a scope distinction: cached account-specific status vs. a compact all-account summary. However, 'status' is left unqualified — it never says what is being reported (progress, queue, errors) — and it does not differentiate itself from siblings like learning_batch_status or runtime_health, which an agent would plausibly confuse it with.

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?

'never browser polling' implies a preference over browser_status/observe_* tools, but it is a fragment with no explicit when-to-use condition, no named alternative, and no guidance on choosing between detail=true and the account-specific vs all-account modes. The agent must infer the routing decision entirely.

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