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

Annotations already declare readOnlyHint, destructiveHint=false and closed-world, so the description is not burdened with the safety profile. It still adds real behavioral context: cost is free, it reads pre-existing organisation data (implying no fresh scan and possibly non-live results), and a 100 requests/minute per-key rate limit that would shape a batching strategy.

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?

Three short sentences, zero filler: scope and return shape first, then cost, then rate limit. Every sentence contributes operationally useful information.

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?

Given only two optional params and no output schema, the description covers defaults and return structure well, plus cost and rate limits. Minor gaps remain: no mention of result caps/pagination, how 'open' is defined, or how fresh the underlying data is.

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 description coverage is 100%, so the baseline is 3. The description adds the meaningful implication that omitting domain searches all sites, which the schema's 'optional' phrasing understates, but severity filtering is left entirely to the enum in the schema.

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 ('Search') and resource ('open issues'), plus the scope ('across all sites (or one site)') and the exact shape of the returned groups (site, issue type, severity, affected page count, example page). An agent can tell this is an issue-search tool rather than a report or scan tool without opening the 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?

Usage is implied by 'open issues' and the note that it reads data already produced, which hints it complements (rather than replaces) scan tools. But it never names an alternative sibling such as get_site_report or get_improvement_plan, nor states when not to use it.

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