set_project_dir

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

With no annotations, the description carries the full burden. It discloses that the tool re-binds subsequent calls, mutates only in-process state, does not write to disk, and is safe to call while unbound. This provides good behavioral clarity, though it could mention if there are any side effects on existing bindings.

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 front-loaded with the key purpose and structured into three paragraphs that each add value. It uses examples and backticks for clarity. While concise, it could be slightly tighter without losing information.

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?

Given that an output schema exists, the description does not need to explain return values. It covers purpose, usage context, behavioral details, and parameter semantics adequately. It is complete for a tool with one parameter and clear effects.

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 one parameter. The description adds meaning beyond the schema by specifying the expected contents of the directory (docs/agents/, .cursor/rules/) and clarifying it does not need to be an initialized project. This enriches the parameter's semantics.

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?

Description clearly states 'Pin the project root for this MCP session' with a specific verb, resource, and scope. It differentiates from siblings by being the only tool that sets the working directory, and it explains the symptom that triggers its use.

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?

Provides clear context on when to use (when unbound_report shows wrong path) and what it does (no editing of mcp.json). It does not explicitly list alternatives or when not to use, but the context is sufficient for correct invocation.

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