recommend_install

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

No annotations are provided, so the description carries the full burden. It transparently states that the tool only recommends rather than installs, and it reveals a decision principle: it avoids over-recommending when a subset suffices. This goes beyond the tool name and provides useful behavioral context, though it does not mention any limitations such as reliance on an available installation catalog.

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 with no filler. The first sentence states the core purpose, the second explains the mechanism, and the third adds a valuable behavioral nuance. Information is front-loaded and every sentence earns its place.

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 a single parameter and an output schema, the description covers the input format, the recommendation scope, and the conservative behavior. It does not discuss prerequisites like needing an inventory of available tools or relationship to sibling tools, but these are not essential given the schema and output schema presence. Slightly more detail about what information the recommendation is based on would make it fully complete.

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%: the only parameter, task, is described as 'Natural-language description of what the user wants to do.' The tool description effectively repeats this same meaning. Since the schema already fully documents the parameter, a baseline of 3 applies; no additional semantic depth is added beyond restating the input.

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 and resource: 'Recommend which profile, modules, or individual tools to install.' It clearly states the tools scope from full profiles down to individual tools, and this differentiates it from specialized siblings like suggest_for_ctf or suggest_for_bounty. The purpose is unambiguous and not a tautology.

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 clear context for when to use it: when a natural-language description of the user's goal needs an installation recommendation. It also implies a useful condition ('Avoids installing everything when only a subset is needed') without explicitly naming alternatives or exclusions. It could be stronger by contrasting with suggest_for_ctf or suggest_for_bounty, but the usage context is evident.

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