set_project

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

With no annotations, the description fully discloses behavior: 'In-memory only — no files are created or modified. The binding is per-connection: setting project A in workspace-1 does not affect workspace-2.' It also mentions the override mechanism.

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 sections and bullet points. It is front-loaded with the main purpose. While not extremely concise, every sentence adds value and there is no redundancy.

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 presence of an output schema, the description details return values: 'Active project name, chunk count, and docs path on success. Lists available projects and suggests setup_project() on failure.' It also references related tools, making it complete for a setter tool.

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 input schema has one parameter 'name' with 0% description coverage. The description adds 'name: Name of a registered project (see list_projects())', providing context that the value should come from a list. This is helpful, though format details could be more explicit.

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 'Bind all subsequent tool calls in this session to a specific project.' It uses a specific verb-resource pair and distinguishes from sibling tools by mentioning setup_project() and get_active_project().

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 explicitly says 'Call at the START of every session.' It provides alternatives: 'Use setup_project() to create a new project. Use get_active_project() to check the current binding.' It also explains overriding behavior with the project= parameter.

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