Use secrets without seeing them (exec / http)

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

With no annotations, the description carries the full burden and does so well: approval requirement on a local page, exact-fingerprint matching and optional remembering, redaction across raw/base64/hex/url-encoded/quoted variants, size-limiting, and the allowlisted-host constraint. These are the operational traits an agent must know before invoking an egress-with-secrets tool.

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?

Dense but front-loaded: it leads with what the tool does, then mode-specific mechanics, then the approval and redaction behaviors. Every clause is information-bearing for a 13-param tool, though the mode syntax could be tightened.

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?

No output schema exists, yet the description adequately covers the return contract (redacted, size-limited) and the approval lifecycle. For a 13-param, no-annotation tool it leaves minor gaps around timeout behavior, cwd, and the names/redact_env_files params, but nothing that would cause a misinvocation.

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 a moderate 69%, and much of the description's parameter detail (exec argv without shell, env/stdin secret injection, http url/headers/body) mirrors what the schema's own field descriptions already state. It adds little for cwd, names, timeout_ms, and redact_env_files, so it neither amplifies nor compensates substantially.

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 action ('runs an action with secrets resolved inside this server') and enumerates the two concrete modes, exec and http, each with its mechanics. An agent can tell this is the secret-injection egress tool. It does not explicitly differentiate itself from siblings like ssh_exec or web_capture, keeping it just short of a 5.

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 clear operative context: which mode to use for process execution vs HTTP, how ${secret:name} interpolates per mode, and the approval condition for any new action. It lacks explicit exclusions or named alternatives (e.g., 'use web_login for captured logins'), so it is clear context without routing guidance.

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