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

Goes well beyond the readOnlyHint/destructiveHint annotations by disclosing that the call is free and exempt from the per-minute limit, that only same-API-key jobs are visible, and what each terminal/non-terminal status means. It also warns explicitly not to resubmit on submit_unknown and tells the agent to follow next_action.

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-loads what the tool does and its cost profile, then packs status-specific guidance into a compact semicolon-separated paragraph. Every clause is actionable and 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?

With no output schema, the description carries the full return-shape burden and does so: results rows, next_page_token for paged actions, error.reason, error.charged, and next_action. An agent has enough to call the tool and interpret all meaningful responses.

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?

The single job_id parameter has 100% schema description coverage, and the description adds only the provenance context that it comes from everyinfra_call_api(mode=async). With the schema already documenting the parameter, the baseline 3 is appropriate.

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 (Read) and resource (a job), and ties it directly to the originating tool by naming everyinfra_call_api(mode=async). This clearly distinguishes it from siblings like everyinfra_call_api, everyinfra_requests, or everyinfra_usage.

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?

Explicitly says when to call based on job status: retry later for submitting/running/finalizing, stop for succeeded, inspect error.reason/charged for failed, and do not resubmit for submit_unknown. This turns the tool into a complete polling protocol rather than leaving the agent to infer behavior.

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