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

Annotations already declare readOnly, idempotent, closed-world, so the safety profile is covered. The description adds real context beyond that: demo sites are excluded from results and rows are pre-sorted by attention priority, which affects how the agent should interpret the first entry.

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, with the imperative 'Start here' front-loaded and the follow-up routed last. The long field list is dense but every item tells the agent what it will receive, so no sentence is wasted.

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?

There is no output schema, and the description compensates by enumerating the returned fields and the ordering, plus the scope exclusion. For a zero-parameter read tool with annotations covering safety, an agent has everything needed to call it and interpret the result.

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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. It correctly implies a no-argument call scoped implicitly to the signed-in user's organizations.

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 resource ('all websites of the signed-in user's organizations') and enumerates exactly what each row carries (site id, status, health score, open critical tasks, open root causes, AI share, last scan). The exclusion of demo sites and the sort order ('what needs attention first') further sharpen the identity, so an agent knows this is the portfolio overview rather than a plain site list.

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?

'Start here' gives an explicit entry-point instruction, and 'Then call get_site_brief for a site' names the natural follow-up tool. What's missing is differentiation from the sibling list_sites, which an agent could plausibly confuse with this tool; no explicit when-not guidance is given.

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