sieve_vault_run

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

With no annotations, the description carries the burden. It discloses that secrets are injected as env vars and that stdout/stderr are not returned. However, it does not mention potential side effects, authentication requirements, or error handling.

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?

Two sentences with no unnecessary words. Every phrase adds meaning: 'with macOS Keychain-resolved secrets injected as env vars' and 'stdout/stderr content is never returned'.

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 input (command and fingerprints) and output (exit code and line counts). It lacks error scenarios or execution environment details, but for a 2-param tool with no output schema, this is fairly complete.

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 baseline is 3. The description adds value by explaining that fingerprints are used to inject secrets from Keychain, clarifying the purpose beyond the parameter descriptions. It does not add syntax details but reinforces the role.

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 executes a command with secrets injected from macOS Keychain, and specifies what is returned (exit code and line counts) and what is not (stdout/stderr). This distinguishes it from siblings like sieve_check_text or sieve_redact_text.

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 implies usage for running commands with secure secrets, but does not provide explicit guidance on when to use this tool vs alternatives, or when not to use it.

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