wait_for_task

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavior beyond that: timeout leaves the job running, output tail is optional, and the initial/status/output reads use SEMAPHORE_TIMEOUT separately from the polling budget.

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?

Four short sentences, front-loaded with the core behavior, then the key constraints. Every sentence adds useful information with no repetition or filler.

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 polling tool with no output schema and rich annotations, the description covers the essential lifecycle (terminal states, timeout leaving the job running) and important timeout/read semantics. It is not fully complete because it does not describe return shape or the role of each parameter, but the core calling behavior is well covered.

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%, so the description must carry parameter meaning. It clarifies timeout behavior and optional output tail semantics, but it does not explain project_id, task_id, poll_interval, include_output, tail_lines defaults/ranges, or how the two timeout concepts map to parameters. Most of the 6 parameters remain ambiguous.

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 uses a specific verb and resource: 'Poll a task until success, error, stopped, or timeout.' It also states what the tool does not do ('Does not start or stop jobs'), which distinguishes it from create_task and stop_task. It does not explicitly name get_task or get_task_output, so the sibling differentiation is good but not complete.

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?

It gives clear when-to-use context (wait for a task to reach a terminal state) and a clear exclusion ('Does not start or stop jobs'). However, it does not route the agent to alternatives, such as using get_task for a single status check or get_task_output for non-polling output retrieval.

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