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

Annotations already signal that this is a mutating, non-idempotent operation; the description adds value by disclosing a key behavioral nuance: using `generatePassword` keeps the secret out of the conversation and returns only the credential reference. It also hints at post-creation constraints by telling users to set `allowedHosts` for broker-usable credentials, complementing the annotations without contradicting them.

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?

Three sentences with no filler: the first states the core operation, the second gives the most security-relevant creation pattern, and the third covers the broker-access prerequisite. Each sentence earns its place and the most important guidance is front-loaded.

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?

Given the tool's complexity — 14 parameters, nested payload objects, multiple credential types, and an output schema — the description covers the essential decision paths: choosing the type, providing the matching payload, generating passwords securely, and setting allowedHosts for brokerable credentials. It does not enumerate every payload field, but the schema and output schema carry that burden; the description is complete enough for correct invocation.

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 100%, so the baseline is 3. The description adds meaningful cross-cutting semantics beyond the schema: it explains the relationship between `type` and the payload blocks, recommends `generatePassword` over `login.password`, and ties `allowedHosts` to downstream exercise via vault_credential_use. This provides selection guidance that the flat property descriptions do not convey.

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 opens with a specific verb and resource: "Create a new credential in an agent vault." It clearly distinguishes this creation tool from its update, get, list, search, and use siblings, and the rest of the description reinforces scope by naming the credential types and payload blocks involved.

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 gives actionable usage guidance: pass `type` plus the matching payload block, prefer `generatePassword` for login credentials, and set `allowedHosts` for api_key/oauth_token credentials so they can be exercised via vault_credential_use. It does not explicitly state when not to use this tool versus an alternative, but the creation context and cross-reference to vault_credential_use provide clear directional context.

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