codeCompletion

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is established. The description adds that the tool 'needs the source and the position, exactly like the editor,' which clarifies the stateless, read-only nature and input prerequisites. But it does not disclose potential failure modes, rate limits, or what happens on invalid input, so the added behavior context is moderate.

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 a single, information-dense sentence with no filler. The core purpose is front-loaded, and the sibling comparisons are placed after the main definition. Slightly run-on but still concise and well-organized for the amount of context it conveys.

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?

The description explains the purpose and input relationship to the editor, and differentiates siblings, which is helpful. But with no output schema and 0% schema coverage, it fails to specify the return shape or how results are represented, and leaves the sourceUrl parameter semantically dark. This is adequate for deciding when to call it, but not complete for reliably invoking it with full understanding.

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?

With schema description coverage at 0%, the description must compensate for the undocumented parameters. It maps 'source' and 'position' to source, line, and column, and 'exactly like the editor' gives some context for line/column indexing. However, sourceUrl is left unexplained, and the description does not clarify the units or whether line/column are zero-based. Thus compensation is partial at best.

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 what the tool does: 'Completion proposals for a cursor position: what may be written at line/column of this source.' It names the resource (source code) and the specific operation (completion proposal). It also distinguishes itself from siblings by explicitly contrasting with codeCompletionFull (adds insert text) and codeCompletionElement (details of one proposal), so an agent can tell them apart.

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 gives context for when this tool is valuable: 'worth having when composing a call against an unfamiliar interface.' It also implies selection guidance by noting what the siblings add, which helps an agent choose between this and codeCompletionFull/codeCompletionElement. However, it does not explicitly state conditions for preferring the alternatives or any exclusions.

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