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

The sentence "unsupported checks are reported as unsupported, never as passed" is genuinely useful behavioral disclosure about how partial results are surfaced, which the annotations don't cover. However, "harmless" sits awkwardly against destructiveHint=true, readOnlyHint=false and idempotentHint=false — the description never explains what state the run may create or destroy, nor that retries without idempotency_key can duplicate work.

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, no filler, purpose front-loaded and the substantive caveat immediately after. Every sentence carries 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?

For an open-world, non-idempotent, destructive-flagged operation that can be pointed at production, the description omits which targets are actually supported and what the result looks like (no output schema). An agent knows the intent but not the blast radius or the expected response.

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 75% and company, environment and idempotency_key are documented in-schema; the description adds essentially nothing about them. It also doesn't say which of the `targets` enum values (credentials, providers, slack, messenger) count as "supported" or what happens when only some are supported, even though that is the most decision-relevant parameter.

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?

"Run supported harmless checks" gives a verb and an object, and the second sentence clarifies partial-support behavior. But "checks" is undefined — nothing says whether these are credential/provider/Slack/Messenger verifications or how this differs from the numerous capability_checks_* and various *_verify siblings. An agent can guess the domain from the schema but not from the description.

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?

There is no guidance on when to run this versus summer_capability_checks_test, summer_guides_hosting_verify, or the capability_checks_* family, and no caution about running against the production environment even though `environment` accepts it. The agent gets no when/when-not framing.

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