open_project

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

With no annotations, the description carries the full burden and does well: it discloses the side effect of starting a session, the permission requirement to save, and the read/create limits on agent behavior. It omits failure behavior and whether an already-loaded project is reloaded or reused.

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?

A single dense sentence that front-loads the primary action, then the conditional branch, then the permission and agent limits. No filler or repetition.

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 tool with no output schema and no annotations, the description covers the key decision points an agent needs: when it joins vs. starts, and the save-right gate. It could say what is returned (session info?) to make the post-call state fully predictable.

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%, so both parameters (server, project) are already documented with defaults in the schema. The description frames 'project' as a key or name in context but adds no syntax or format detail beyond what the schema provides, which is the expected baseline.

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 specific verb and resource ('Open a project on the server') and immediately explains the two operating modes: joining a running session, or loading files and starting one. This lets an agent distinguish it from siblings like join_session or list_projects without opening any schema.

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 conditional guidance ('when none is running, load its files and start one') plus a prerequisite ('only with the right to save it') and a hard boundary ('Agents never create projects or save'). It stops short of naming alternative tools such as join_session or list_projects for the cases this tool does not handle.

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