list_projects

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

The readOnlyHint annotation already indicates a safe read operation, and the description adds meaningful behavioral nuance beyond it: recursive descent skips hidden directories, default behavior checks only the directory and immediate children, and an empty array is returned when no matches exist. This is solid behavioral disclosure for a read-only discovery tool.

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 compact and front-loaded with the core purpose, then covers usage distinction, recursion behavior, and return format in just three sentences. Every sentence earns its place with no filler or repetition of schema content.

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 simple read-only discovery tool with two well-documented parameters and no output schema, the description is complete: it states input behavior, edge cases (hidden dirs, no matches), and the exact return shape. The agent has all necessary information to invoke the tool correctly without additional context.

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%, so the schema already documents both parameters. The description adds value by explaining the semantic effect of recursive=true versus the default, including hidden-directory skipping. The directory parameter could use a little more elaboration, but the recursive parameter is meaningfully enriched beyond the schema.

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 a specific verb and resource: finding Godot projects by locating project.godot files. It also explicitly differentiates from check_project ('for inspecting a known project, use check_project'), resolving a key sibling ambiguity. The return shape is included, which further sharpens purpose.

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 explicitly says when to use this tool: 'Use to discover available projects when the user has not specified one.' It also gives an exclusion and an alternative: for inspecting a known project, use check_project. Recursion behavior is also defined, removing any need for the agent to guess.

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