Poll a login job

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

Annotations already declare readOnlyHint and idempotentHint, so safety is covered. The description does add useful non-annotated context — the required API key scope (accounts:read) and the underlying GET endpoint — but says nothing about what statuses are returned, whether job results expire, or any rate limit on repeated polling, which is the behavior an agent most needs for a polling tool.

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?

Short and front-loaded: the purpose leads, the auth scope and endpoint follow as compact supporting facts. The one redundancy is that the first line duplicates the title verbatim, but the rest of the text earns its place.

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 single-parameter read tool with no output schema, the definition covers enough to invoke it, and the endpoint plus auth scope add real context. It falls short on the return side — an agent polling a job needs to know the status vocabulary or at least that terminal states exist — and on the mismatch between the camelCase operation names cited and the actual sibling tool names.

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% and jobId has no description in the schema, so the description must carry the meaning. It does partially compensate by telling the agent jobId is the identifier returned by createAccount, reloginAccount, or checkAccountSession, which is genuinely useful provenance, but it never states the ID's format, uniqueness scope, or what happens with a stale/unknown ID.

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 opening line pairs a specific verb (poll) with a specific resource (a login job), and the closing line narrows it further by naming the operations that produce such jobs (createAccount, reloginAccount, checkAccountSession). That distinguishes it from siblings like check_account_session or relogin_account, though the camelCase names don't match the snake_case sibling tool names an agent actually sees.

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?

Usage context is implied rather than stated: the mention of jobs returned by account creation/relogin/session-check tells an agent roughly when this applies, but there is no explicit 'call this after X until status is Y' guidance, no polling cadence, and no statement of what to do when the job is already finished or expired.

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