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

Goes well beyond the annotations: token is single-use and short-lived, altered fields are rejected, inline bytes must match the approved digest/MIME/length, exactly one business mutation per token, and replay returns the recorded outcome rather than double-writing. This is exactly the kind of non-obvious safety behavior an agent needs before firing a destructive call.

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?

Long but well-structured with Args/Returns/when_to_use/preconditions/post_effects sections and the key action front-loaded. Slightly padded by doubled-backtick markup and some repetition of the digest/field-unchanged rule across Args and preconditions.

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 destructive, token-bound mutation with no schema-level parameter documentation, the description supplies the full contract: sequencing, token semantics, payload shape, upload rules, failure modes, and idempotency behavior. An output schema exists, so the brief Returns note is sufficient.

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 0%, so the description carries the burden, and it does for three of four params: approval_token provenance, the whole execution.payload object including wrapper keys, and the file/native-upload digest requirement. The fourth parameter, correlation_id, is never mentioned anywhere, leaving a small gap.

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 verb and resource ('Execute a previewed entity write or workflow action') and immediately positions itself as 'the single second step' after any preview_* tool, which cleanly separates it from the many preview_* siblings.

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?

Explicit when_to_use ('after a successful preview_* call'), explicit preconditions (valid unconsumed token from the same connection, approved fields unchanged), and a named alternative workflow (run preview_* first). Nothing is left to inference.

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