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

Annotations only say read-only and non-destructive; the description goes well beyond that by explaining the row model (one row per Worker, Pages project, Vercel, Netlify or CI check), that failed rows carry extra details, and that host-connected rows depend on the account plan. This is exactly the operational context an agent cannot get from the structured fields.

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?

It is front-loaded with the core purpose and return shape, then layers the row semantics and the plan caveat. The middle sentences are dense and slightly compressed ("a failed one includes its details"), but no sentence 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 two-parameter read tool with no output schema, the description covers return shape, failure behavior, log handoff and plan gating well. It stops short of stating what an empty result means (no deploy vs. no host connection beyond the plan note) or error behavior for an invalid projectId, which are minor residual gaps.

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% and both parameters are documented there, including the branch default of the live branch and the projectId source (list_projects). The description mentions filtering by branch but adds no format or resolution detail beyond what the schema already provides, so the baseline 3 applies.

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 precise verb and resource: it returns the latest deploy for a branch on the site's host, including state, address and log link. It also names the host providers (Vercel, Netlify, Cloudflare) and distinguishes itself from the sibling deploy_logs by explaining that failed rows carry an id for that tool.

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?

"Check it after the user publishes" gives a clear trigger condition, and the plan-gating note tells the agent when rows will or will not appear (host connections required vs. GitHub checks on every plan). It does not explicitly state when to reach for deploy_logs instead, but the id reference makes the handoff inferable.

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