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

With no annotations, the description carries the full behavioral burden and does so thoroughly: access control ('Only the account that ran the scan can read it'), that an in-progress state is not an error, expected durations for large and small sites, and a precise backoff protocol driven by a field in the response.

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-loaded with purpose and results, then access rule, then timing and polling protocol in a sensible order. The latency statistics are somewhat granular but directly serve the wait-vs-retry decision, so they largely earn their 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?

No output schema or annotations exist, yet the description explains the return shape (status, score, failed checks, category scores, pages with links) and the embedded timing field an agent must act on. Nothing needed to invoke and interpret the call 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?

Schema coverage is 100% and the job_id description already tells the agent where to obtain the value (start_site_scan, list_sites, site_history). The description adds no additional parameter guidance beyond that, so the baseline of 3 applies.

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 and resource ('Read one of the signed-in person's site scans') and enumerates what the read yields: running state, score, failed checks, category scores, covered pages, plus per-page report links. It is clearly distinguishable from siblings that start or request a scan.

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?

Gives concrete when-to-use context ('A scan that is still running is normal, not an error') and an explicit anti-pattern ('Do not poll'), with the correct alternative protocol spelled out (read check_again_after_seconds and wait). It never names competing siblings such as site_history or start_site_scan, which keeps it just short of a 5.

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