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

Annotations only provide destructiveHint=true, so the description carries most of the burden — and it does: it discloses that dry_run=false can create, modify, or DELETE running pipelines and their data, and that the response is the publication row. It does not explain auth/permission requirements or reversibility, so not a full 5.

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?

Every sentence earns its place: the risk profile and default are front-loaded, key tokens are emphasized, and the endpoint and return value are appended compactly with no filler.

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 three-parameter mutation tool with no output schema, the description covers mode semantics, blast radius, default behavior, endpoint, and return shape — nothing an agent needs to invoke it safely is missing.

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, but the description adds meaning beyond the schema by spelling out the consequence of dry_run=false (live catalog mutation, possible deletion of pipelines/data) rather than just 'apply'.

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+resource ('publish a draft') plus the two operating modes, and the WRITE/DESTRUCTIVE framing makes it unmistakably distinct from the read/list siblings (list_drafts, list_publications) and from estuary_create_draft.

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/when-not guidance: dry_run=true (default) validates only; 'Set dry_run=false only when you intend to change live infrastructure.' This tells the agent precisely the condition that selects the risky path.

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