get_completions

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

With no annotations provided, the description carries the full burden. It discloses a prerequisite (file must be opened) and implicitly signals read-only behavior via 'Get'. However, it does not detail side effects, error conditions, or requirements like a running LSP server, so behavioral transparency is only 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 three sentences, each serving a purpose: purpose, content, and usage/prerequisite. It is front-loaded with the core action and remains free of fluff, though the phrase 'Helpful for code assistance' is somewhat generic.

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 tool with four straightforward parameters and no output schema, the description covers the essential usage constraints: location specificity, context dependence, and the prerequisite of an open file. It doesn't explain return format, but the description's 'completion options' sufficiently informs what the response contains for an agent.

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?

The schema already provides 100% coverage with descriptions for all four parameters. The description adds context about what the completions include (variable names, etc.) but does not add new parameter-specific details beyond the schema. Per the rubric, this is a baseline score.

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 opens with a specific verb ('Get') and resource ('completion suggestions'), explicitly scoping to a file location. It distinguishes from siblings like get_diagnostics and get_code_actions by emphasizing completion context (variable names, function calls, object properties). This leaves no ambiguity about the tool's function.

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 provides clear usage context: when to retrieve completions, a concrete example (determining functions available in a package when changing libraries), and a prerequisite (file must be opened). It doesn't explicitly mention alternative tools, but the context is sufficient to guide an agent to select this tool over its siblings.

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