kb_remove_project

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

Goes well beyond the annotations: it clarifies that only index entries are removed and files are untouched (the reason destructiveHint=false is safe), states a precondition (readonly-mode refusal), and discloses audit logging. That covers blast radius, permission/mode requirements, and traceability in one sentence.

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 short sentences, front-loaded with the action and the crucial 'files untouched' qualifier before the secondary operational notes. No filler.

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?

With an output schema present and only one parameter, the description covers enough to call safely: blast radius, mode precondition, and auditing. The remaining gap is path-format expectations and no-op behavior for a path not present in the index.

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% for the single 'path' parameter, so the description bears the burden and only implicitly indicates it is a project-folder path. It doesn't state format (absolute vs. relative, case sensitivity) or behavior when the path isn't indexed.

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 ('Remove a project folder from the knowledge base') plus a scope-defining parenthetical that separates it from file deletion ('index entries only; the files are untouched'). It doesn't name the sibling to prefer for the alternative operation (e.g. kb_reindex/kb_add_project), but the resource is 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 usage context is implied by the resource name, and 'Refused in readonly mode' gives one precondition. There is no explicit when-to-use guidance versus siblings such as kb_reindex or kb_rebuild, which also change index state.

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