close_project

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

Annotations already indicate destructiveHint: true and readOnlyHint: false MendThe description adds valuable context by specifying 'in-memory' and 'without writing changes', clarifying that no persistent side effects occur. This reinforces the destructive nature (session discarded) and indicates the operation is not a save. It provides behavior beyond the bare annotation.

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 a single, compact sentence with no redundant words. It front-loads the core action and its key side effect (no writes). Every word contributes meaningful 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 the tool's simplicity (one required parameter, no nested objects, output schema present), the description is adequately complete. It conveys the essential behavior (discard, no writes) and the in-memory scope. It does not detail side effects beyond 'discard,' but for a close operation, this is sufficient, and annotations cover the destructive nature.

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 description coverage is 0%, so the description needs to compensate. However, it does not mention 'project_id' at all. While the parameter name is self-explanatory, the description does not clarify that this ID must reference an existing in-memory session or how it is used. The tool provides no additional meaning over the bare schema property.

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 the verb 'Discard' and the resource 'in-memory project session', specifying the action (close/discard) and the scope (in-memory, no writes). It distinguishes itself from siblings like save_cxt (which persists) and load_project (which loads), making the purpose unambiguous.

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 implies usage: 'Discard an in-memory project session without writing changes' suggests abandoning changes and closing. However, it does not explicitly state when to prefer this over alternatives (e.g., save_cxt) or any prerequisites (e.g., session must be active). The context is clear but lacks explicit exclusions or comparisons.

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