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

Annotations cover the write/idempotent/non-destructive profile, and the description adds real value beyond them: replace-on-reindex semantics and the metered/paid-plan cost caveat. It doesn't discuss failure modes, size limits, or indexing latency, so it's strong but not complete.

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 clauses, each carrying distinct information: purpose, input shape plus replace semantics, and the metering caveat. Nothing is padded and the purpose leads.

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 two-param write tool with no output schema, the description covers purpose, input mapping, replacement behavior, and cost implications. It omits what the agent should expect back or how errors/partial indexing surface, which keeps it off a 5.

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% with only two required params, so the schema already documents both fields. The description's 'path → content map' phrasing restates what the files property says rather than adding format or edge-case detail. 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 ('Index a project's files for semantic code search (RAG)'), which clearly separates it from read-only siblings like search_project_code and clear_code_index. It stops short of naming an alternative explicitly, so it's clear but not fully sibling-differentiated.

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?

Implies use when you want code searchable via RAG, and notes that re-indexing a path replaces it, but never says when to choose this over search_project_code or clear_code_index. The 'metered — paid-plan feature' note is the closest thing to a prerequisite.

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