run_with_secret

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

With no annotations, the description carries the full behavioral burden and does so thoroughly: two-phase handshake (first call returns a link, second call with request_id waits and executes), the security model (user sees the command before entering anything, only that command receives the values), and the return shape (exit code plus output with every value masked).

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 critical 'when to use this' guidance is front-loaded in the first sentence and the two-phase flow is laid out in sequence. Slightly repetitive in restating the secret concept across the trigger examples and the summary sentence, but nothing is wasted.

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 tool with no output schema, the description compensates by explaining the return values and the asynchronous request_id flow completely. The only gap is that ttl_seconds is undocumented in both the schema description and the description text.

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 80%, so the schema documents most fields itself. The description adds real meaning beyond it by explaining the request_id lifecycle ('call again with the returned request_id') and that names drives which secrets the user is prompted for, though ttl_seconds and cwd get no added context.

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 states a specific verb and resource: it asks the user for secrets and runs exactly one command with them as environment variables. It is instantly distinguishable from a plain secret-request tool because it executes a command, though it never names the sibling tools request_secret or send_secret to make the boundary explicit.

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?

Strong trigger condition is given ('use this whenever a single command needs a password, token, API key') plus a hard rule ('never ask the user to type or paste a secret into the chat'). It stops short of stating when not to use it or which sibling to prefer for the non-command case.

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