add_parallel_learning_accounts

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

With no annotations, the description carries the full burden, and it does disclose real semantics: it will not stop, re-login, navigate or rebuild existing workers, and conflicts are reported rather than overwritten. That is genuinely useful non-destructive context, but nothing is said about permissions, idempotency on duplicate accounts, or what the call returns.

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?

The core action and its non-destructive guarantee are front-loaded in the first two sentences, with the conflict and retry rules following. It is compact with little waste, though the final retry sentence reads as a fragment whose referent tool is unclear.

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?

No output schema and no annotations mean the description must cover behavior and return shape, yet it omits what the per-account object must contain, what happens on partial success, and what the 'reported' conflicts look like. For a mutation tool that ingests an opaque array, this is a significant shortfall.

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 0% for four parameters, and the description explains none of them. Critically, 'accounts' is a required array of untyped objects with additionalProperties:true, so the description had to define the per-account fields, and it does not; 'rate', 'state_dir' and 'browser_mode' are likewise unmentioned.

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 verb 'Append' plus the resource 'imported accounts' and the target 'this supervisor' is specific and tells an agent this is an additive registration step, not a full setup. It implicitly separates the tool from setup_learning_accounts/import_accounts, though it never names those siblings, so the differentiation is left to inference.

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?

'Use retry only for terminal failures' points toward retry_parallel_account and gives one usage rule, and 'conflicting existing queues are reported, not replaced' implies when not to expect replacement. But there is no explicit statement of when to choose this over import_accounts, setup_learning_accounts, or start_parallel_learning_batches.

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