website_green

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true, so the mutation/repeat-safety profile is structured. The description adds genuine extra context: scope-session minting under basic auth, the specific checks performed, and that the result carries no secrets. It does not say what state is modified or whether reruns are safe, so it is adequate but not rich.

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 purpose is front-loaded in the first sentence, which is good. But the remaining sentences are dense internal jargon ('Pour is on', 'doc_key', 'src_keys', 'describe 200', 'a describe 200 is not this check') that costs more parsing effort than it returns, so conciseness is undermined by unreadability.

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?

An output schema exists so return value explanation is not needed, but the description must still be complete enough to call the tool correctly. It fails to document the only parameter, and against 15 siblings it only disambiguates from two, leaving an agent unclear on when this tool applies versus the surrounding suite.

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 single parameter target_dir has 0% schema description coverage and a bare empty-string default; the description never mentions it. With low coverage the description is expected to compensate, and it does not, leaving the agent to guess the format and effect of the one input.

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 specific verbs and a resource (install, start, check the catalog page) and explicitly distinguishes itself from smoke_test_zeus and smoke_test_agent. An agent can see this is a distinct catalog-page check rather than a generic smoke test. It stops short of a fully self-contained 5 because the object of the check ('list cards', 'Pour') is opaque without internal vocabulary.

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?

It carves out a boundary against two named siblings ('Separate from smoke_test_zeus', 'Does not call smoke_test_agent'), which is real routing guidance. However it never states the positive condition for when to run this instead of the other 12 siblings, nor prerequisites, so usage is only implied.

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