project_templates

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so "Read-only" is partly redundant. What the description adds is genuinely useful: the shape of returned rows (key, repo, description, commit-pinned ref) and the exact CLI command producing identical output, letting an agent predict the response.

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?

Two sentences, front-loaded with the verb and resource, then the row shape, then the downstream usage. Nothing is filler; the CLI equivalence is compactly stated.

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?

With no output schema, the description compensates by enumerating the returned fields, including the conditional ref for commit-pinned templates. For a zero-param read tool this is everything an agent needs to call it and use the result.

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?

Zero-parameter tool, so the baseline is 4; the schema has no properties to explain. The description still adds meaning by clarifying that a returned key is the value to feed into project_init's template argument.

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?

Specific verb+resource ("List the starter templates project_init can clone") with the exact payload path (data.templates) and per-row fields. It is unmistakably distinct from siblings like project_info, stack_list, or project_init because it names the cloning relationship explicitly.

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?

Clear context: use this to discover template keys and then pass a key to project_init's template parameter, plus a CLI equivalent (`flisk project --list --json`). It lacks an explicit exclusion (e.g., when to use project_info instead), so it stops short of the top band.

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