get_deployment

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

The description adds substantial context beyond the annotations: MCP-owned background execution, wait-and-loop semantics, status_changes and restarts_seen on services, files_uploaded behavior after uploads, resume=false as observe-only, and that environment-variable values are never returned. The annotations already declare destructive/openWorld behavior, but the description does not fully spell out the destructive consequences of the default resume path.

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?

The description is dense but nearly every clause carries operational information, and the deployment_id case is front-loaded. However, multiple modes are packed into a single paragraph with semicolons, so structure could be improved for faster scanning.

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 does a good job explaining return contents for the no-argument map view and project view, plus service fields and the env-var exclusion. It does not fully detail the deployment_id observation result shape, leaving a moderate gap for a complex seven-parameter tool.

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?

It covers all seven parameters with meaning beyond the schema: deployment_id triggers observation/wait, wait_seconds has a 20-second cap and loop guidance, files_uploaded is tied to sync/upload, desk_url/project_id scope the project view, application_id narrows to one app, and resume=false observes only. This compensates well for the low 29% schema description coverage.

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?

The description states specific operations: observe/wait for background execution with deployment_id, and return deployment/project maps with no args or desk_url/project_id. It is clear enough to distinguish from deploy_app/start_app by focusing on observation and status rather than initiating deployments, though it does not name siblings explicitly.

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?

It explicitly maps arguments to usage scenarios: deployment_id for observe/wait, wait_seconds max 20 with a call-again loop, no arguments for the full deployment map, desk_url/project_id for project view, and application_id for a single application. It also gives concrete post-action guidance such as setting files_uploaded=true after sync_files and not answering the user while execution is still in the background.

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