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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real context beyond them: it discloses the specific data sources read, the server-side nature of the wait, and the kind of correlated findings produced. It does not state permission/auth requirements or failure behavior when the deployment id is unknown, and the fact that it hits the public URL is a slight tension with openWorldHint=false, though the URL belongs to the managed resource.

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?

Front-loaded with the one-call purpose, then the alternative-routing rule, then the rationale. It is a dense paragraph and the parenthetical examples (healthy log next to a 500 page, silent app port during install) earn their place by conveying the tool's unique value, though the sentence runs long.

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?

With no output schema, the description correctly carries the burden of saying what comes back by enumerating the five diagnostic sections, and it explains the waitSeconds payoff. The remaining gap is the undocumented id parameter and no guidance on behavior for invalid or missing deployments.

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 description coverage is only 50%: waitSeconds is documented in the schema, but id has no description anywhere, and the tool description never explains that it is the deployment identifier or what form it takes. The description also does not reinforce the waitSeconds semantics (settling before read, early return on death/idle), leaving the description to add essentially nothing over the schema.

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?

"Everything needed to answer 'what is wrong with this deployment', in ONE call" is followed by a concrete inventory of what is collected: live state, RAM and CPU, cleaned log tail, startup config, and public URL response. It explicitly names the four sibling tools it replaces, so an agent can distinguish it from deployments_get, deployments_logs, deployments_check, and deployments_getStartup without opening any schema.

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 an explicit routing rule ("Use this INSTEAD of the deployments.get + deployments.logs + deployments.check + deployments.getStartup sequence") and a default entry point ("Start every investigation here"). It also explains why the combined read beats the individual calls, with concrete examples of cross-signal findings that no single tool can produce.

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