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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's job is to add consequence detail — and it does: search silently returns nothing until re-indexing, and project files survive. That is exactly the post-destruction state an agent needs. It stops short of noting permissions, whether the project must be indexed at all, or whether removal is async.

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?

Three short sentences, front-loaded with the action, then the consequence, then the safety boundary. Every sentence adds distinct information with no repetition of the name, title, or annotations.

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?

For a one-parameter destructive mutation with no output schema, the description covers what is destroyed, the observable aftereffect, and what is preserved — enough to call it correctly. Minor gaps remain around preconditions (must the project exist / be indexed) and whether the operation blocks.

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 a single documented 'project_id' (UUID), so the schema already carries the parameter semantics. The description adds no format, scope, or validation detail beyond it — baseline 3 applies.

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: 'Delete every embedding for a project.' It also scopes what is NOT affected ('Project files are not touched'), which distinguishes it from destructive siblings like delete_project. It never names the inverse tool (index_project_code), so it falls just short of explicit sibling differentiation.

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?

'Code search returns nothing until the project is indexed again' implies the intended workflow (use before re-indexing), but usage is only inferred, not stated. No explicit when-to-use, when-not-to-use, or named alternative such as index_project_code.

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