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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds cost ('Free.') and a state machine the agent must interpret (quick vs. deep pass states) that no annotation conveys. It stops short of describing response shape or whether a 'missing' state is recoverable.

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?

Two sentences, front-loaded with the returned fields and followed by the operational sequence; the trailing 'Free.' is terse and useful. The first sentence is a comma-heavy list that reads as a run-on but carries no 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?

With no output schema, the description must carry return semantics and it does: it names the flag, timestamps, sub-pass states, and the gate for the next run, plus the follow-up call. Nothing an agent needs to poll and branch correctly appears to be 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?

Schema coverage is 100% and the single 'site' parameter is documented in the schema with its allowed value. The description only echoes 'for the site' without adding format or constraint detail, so the baseline 3 for schema-driven coverage 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?

The description states a specific verb+resource ('keyword research status') and enumerates exactly what it reports: processing flag, start time, quick/deep pass states, and next-run eligibility. An agent can distinguish this from data-returning siblings like get_research_run or get_keywords without opening any schema.

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?

Explicit sequencing is given: 'Poll this after run_keyword_research' and a machine-checkable transition condition ('when processing is false and deep.status is "complete", call get_keywords'). That is strong when-to-use guidance, but it does not say when to prefer this over get_research_run or list_research_runs, which are the closest alternatives.

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