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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds the non-obvious facts that this read is sensitive (it pulls a secret into context) and that revealability is not guaranteed for legacy keys. That is meaningful value beyond the structured hints, though it says nothing about authorization requirements.

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 short sentences, zero waste, with the sensitivity warning and the failure mode front-loaded before the fallback prohibition. Every clause carries actionable 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?

An output schema exists, so return values need not be described. For a one-parameter sensitive read, the description covers the key risks (secret exposure, legacy-key failures, wrong alternative), leaving only the parameter's meaning unaddressed.

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 0% and the single appId parameter is never mentioned in the description, so nothing in the text explains which app's key is fetched or the identifier's format. The parameter name is largely self-explanatory, which keeps this at an adequate rather than poor level, but the description does nothing to compensate for the schema gap.

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 ('reveal an existing SDK key') plus a scope qualifier ('sensitive read... into your assistant context'). An agent can distinguish this from regenerate_sdk_key and get_sdk_setup, which are the closest siblings, without opening any 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?

Gives an explicit failure-mode condition ('legacy keys may not be revealable') and a clear exclusion ('never rotate as a fallback'), which routes the agent away from regenerate_sdk_key. It stops short of stating the positive trigger (when the caller actually needs the key value), but the guidance is concrete rather than implied.

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