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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context: the hosted transport cannot read the working tree, and the tool returns current projects instead of pushing. It never resolves the tension between a tool named 'push_project' and a read-only hint, but it does not contradict the annotations either.

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 a single sentence, and the key constraint ('Hosted transport cannot read your working tree') is front-loaded. But it crams login steps, push commands, an alternative server mode, and the return value into one dense line without clean structure.

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?

An output schema exists, so return values need not be spelled out, and the description does address the hosted-transport constraint and fallback. What remains incomplete is the core identity of the tool: an agent still cannot cleanly tell whether push_project moves code or just lists projects.

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?

The tool takes zero parameters, so the schema is trivially complete and there is no parameter semantics for the description to add. Baseline 4 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?

The description ultimately states the tool's real behavior ('Returns current projects instead'), but its center of gravity is a CLI push walkthrough, so what push_project actually does is buried and ambiguous. It also never distinguishes itself from siblings like status, check_project, or build, which is confusing given the name implies a mutation.

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 routes the agent away from this tool for real pushes ('push from where the code lives') and names concrete alternatives (npx CLI, the stdio server nomac mcp), which is useful. However, it never says positively when to call push_project itself versus those alternatives, so the usage guidance is only implied.

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