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

Annotations already cover readOnlyHint, idempotentHint, and destructiveHint, so the description's additional details about being FREE and the refusal behavior when re-calling start during RUNNING add genuine context beyond the structured fields. It does not contradict any annotation. A 4 reflects that it is highly transparent but doesn't describe every edge case.

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 description is three sentences: the return value, the polling guidance, and the cost/refusal warning. Each sentence earns its place, the most important information is front-loaded, and there is zero redundancy.

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 simple status-check tool, the description covers return fields, polling cadence, a critical guardrail, and cost. The output schema exists to document the response format. Nothing an agent needs to call it correctly is missing.

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 input schema provides a thorough description of projectId, including format, examples, and guidance to call seo_project_list if needed. Since schema coverage is 100%, the description itself adds no additional parameter semantics. Baseline 3 is appropriate because the schema carries the full burden.

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 clearly states the verb 'Returns' and the specific resource 'the most recent background job for a project', then enumerates the returned fields (type, status, progress counters, last log line). It implicitly distinguishes itself from sibling start tools (seo_audit_start, seo_content_generate, etc.) by describing a polling operation rather than a job initiation.

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 tells the agent when to use this tool ('Poll this every few seconds after any tool that starts a job') and provides a critical negative instruction ('Do NOT re-call the start tool while status is RUNNING'). It also clarifies the consequence (refusal), leaving no ambiguity about the correct invocation pattern.

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