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

Goes well past the annotations: it discloses the 500-file / 5 MB limits, that .env files are actively rejected, that a missing denkops.json creates a new project, and the naming fallback order (name, package.json, pyproject.toml). It also states the return value (live URL), which the annotations cannot convey since there is no output schema.

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-loads the action and outcome in the first sentence, then the branching rule (project_id), then the hazard (.env), then the hard limits. Dense but every clause carries information and nothing is repeated from the schema.

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 write operation with no output schema and nested file objects, the description covers action, input shape, failure conditions, limits and the return value. An agent could invoke it correctly from this text alone.

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?

Adds real meaning beyond the 67%-covered schema: it explains how `name` interacts with denkops.json, when `project_id` applies, and that `files` must include every source file rather than a delta. Only minor gap is it does not mention the `encoding` enum, which the schema covers on its own.

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?

Opens with a specific verb and resource ("Deploy a project to DenkOps by sending its files") plus the outcome ("get the live URL back"). It is clearly distinct from siblings like redeploy, rollback, start_project and list_deployments, since it is the only tool that takes a file payload.

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 clear routing logic: omit project_id to create a new project, pass project_id to ship a new version of an existing one, and .env files are rejected so env vars should be set separately. The gap is that it never names the `redeploy` sibling or explains when re-uploading files beats redeploying an existing build.

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