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

The description is fully transparent about side effects and non-read-only behavior. It states that a request is created, that a fill link may be emailed to the org owner, and that a credentialId is returned upon fulfillment. It also guarantees the secret is never seen by the agent or LLM. These details go beyond the annotations and do not contradict them (readOnly=false, idempotent=false, destructive=false).

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 description is moderately dense but well-organized: it opens with the core purpose, then explains the conditional behavior and the required follow-up action, and closes with a clear use case. It avoids fluff and every sentence contributes necessary detail. It is slightly long due to the conditional workflow, but this is justified by the tool's complexity.

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?

The description covers the main workflow and the key decision point (inline elicitation vs. fill link). It gives enough detail for an agent to understand the flow and when to poll. However, it does not mention cancellation (a sibling tool exists) or what happens when ttlSeconds expires, and it does not clarify how the agent distinguishes between the two modes in the response. These are minor gaps given the presence of sibling tools and an output schema.

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 input schema already provides descriptions for all six parameters, achieving 100% coverage. The tool description adds some context for ttlSeconds and notifyOwner by mentioning the fill link and emailing the org owner, but largely mirrors the schema. Since the schema is comprehensive, the description does not significantly add meaning beyond what is already structured, so the baseline score of 3 is appropriate.

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 description clearly states the tool's purpose: request a credential from a human without the agent/LLM seeing the secret. It distinguishes itself from related siblings like vault_credential_create by emphasizing that the secret is never exposed to the agent, and it specifies the credential types involved. The verb 'request' and resource 'credential from a human' make the action specific and unambiguous.

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?

The description explicitly says 'Use this when a flow needs a secret the agent doesn't hold and can't safely be given,' giving a clear usage condition. It also explains the two possible workflows (inline elicitation vs. fill link with polling) and directs the agent to poll vault_credential_request_status when a fill link is returned. However, it does not explicitly mention when not to use it or name alternatives like vault_credential_create, so it lacks a small piece of explicit contrast.

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