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

The description goes well beyond the annotations, disclosing that the key is exposed to the client runtime and its host, that method only feeds a release-policy check and does not restrict later use of the key, that retrieval creates audit events, and that revocation only blocks future retrieval rather than invalidating already-issued keys. Those are exactly the security-relevant behaviors an agent needs and none are available in the structured fields.

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 and each subsequent sentence delivers a distinct fact — exposure surface, method semantics, key_name rules, audit side effect, revocation limits. There is no filler or restatement of the schema or annotations.

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 a security-sensitive retrieval tool with no output schema, the description covers what is returned (the actual key, to client runtime and host), what side effects occur (audit events), and what the scope of revocation is. Nothing an agent needs in order to call it safely is missing.

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%, so the description must carry the burden, and it does for two of three parameters: method's purpose is clarified as a policy check rather than request execution, and key_name's conditional requirement is spelled out per auth type. The service parameter is only implicitly explained through 'provider credential ... for a service', leaving its expected format or accepted values unstated.

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?

The opening sentence gives a specific verb and resource: 'Retrieve an authorized stored provider credential.' That is unambiguous and distinct from get_identity and list_audit_events by resource alone, though the description never explicitly names those siblings or states the boundary with them.

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 supplies a clear usage trigger ('when the user needs a key for a service') and conditional rules for key_name: OAuth connections require an explicitly approved key_name, while manual agent tokens may omit it to select the primary credential. It stops short of explicit when-not-to-use guidance or naming alternatives.

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