deploy

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

Annotations indicate destructiveHint=true, and the description goes far beyond that by explaining the exact behavior: creates a tar.gz archive, uploads (max 50 MB), auto-detects framework, builds Docker image, uses blue-green deployment, keeps old container until health checks pass, and excludes files matching .gitignore/.sotaignore. It also details the auto-injected database environment variables. No contradiction with annotations.

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 well-structured with clear sections and bullet points for framework detection. It is front-loaded with the purpose and then dives into details. However, it is somewhat verbose, especially the section on database environment variables which could be shortened. Still, every sentence earns its place by providing necessary operational context.

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?

The tool has no output schema, and the description does not mention what the response or return value of the deploy call is. It also does not explicitly state error conditions, failure modes, or what happens if the upload fails. Given the complexity of the tool (deployment with blue-green, health checks, etc.), the description should include what the agent can expect back (e.g., a deployment ID, status, or confirmation). The absence of this information makes it slightly incomplete.

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% with both parameters described. The description adds context about the directory needing to contain app source code and mentions that project_id can be found via list-projects, but this mostly repeats schema descriptions. It does not add new semantic constraints beyond what is in the schema, so baseline 3 is appropriate.

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 clearly states 'Deploy an application to sota.io' and explains the entire process: creating an archive, uploading, auto-detecting framework, and building a Docker image. This is a specific verb-resource pair that distinguishes it from all sibling tools (none of which deploy).

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?

The description provides extensive guidance on when to use this tool, including framework detection, the requirement to listen on the PORT environment variable, and the blue-green deployment strategy. It also explicitly mentions using 'get-logs' to monitor build progress, steering the agent to an alternative tool for monitoring. The description covers prerequisites, supported frameworks, and custom Dockerfile usage.

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