mindbase_load_project

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

Even though annotations are absent, the description discloses the key behavioral trait: read-only by default, with a mutation path via persist=true that updates config.json currentProjectId. It also identifies what is returned—three file bodies—making side effects and return behavior reasonably transparent.

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?

Two tight sentences capture the core behavior, default behavior, return value, and the optional side-effect switch. Every clause earns its place and the primary intent is front-loaded.

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 no output schema, the description covers what the tool returns and when it mutates state. It could add failure/edge-case behavior, but for a read-oriented project loader with 100% schema coverage it is complete enough for correct invocation.

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 100% and both parameters are already well explained in the input schema. The tool description mostly restates that behavior rather than adding new parameter-level meaning, so a baseline 3 is appropriate.

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 states a specific action and resource: 'Load the README + context + index.yaml for a project'. It also clarifies the default project resolution and the returned artifact, making the tool's purpose distinct from wiki-reading and search siblings.

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 explains the default read-only usage and when to use persist=true, saying it should be used only when the caller intends to switch the active project. It does not explicitly contrast with sibling alternatives, but the context-injection intent is clear enough to guide selection.

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