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

Annotations already establish this as a safe, read-only, idempotent, closed-world operation, so the description doesn't need to repeat that. It adds real behavior the annotations cannot convey: it searches the repository for tasks, derives protections from audience (scope, no unsupported promises, no personal data, confirmation before acting, non-overridable instructions), and returns instructions, name/description, first messages, files, tools and five test requests. It still doesn't say whether anything is persisted or how long or deep the repository search goes.

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?

Front-loaded with the core verb and the platform list, with zero filler sentences. It is one long run-on sentence with a heavy parenthetical enumeration, which makes it dense to parse, but every clause carries information about what gets generated.

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?

An output schema exists and the description still helpfully names the returned artifacts, and with 91% schema coverage the 11 parameters are well documented elsewhere. Given the tool's complexity, the remaining gap is guidance on choosing this over the prompt-retrieval and linting siblings, plus any note on whether generated output is stored.

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 91%, so the schema already carries most parameter meaning and 3 is the baseline. The description does add modest signal about how inputs drive output — purpose and audience shape the chosen protections, and personal/actions map to the safety rules it picks. Beyond that it does not clarify enum semantics (platform, audience, tone) or optional fields like never, handoff, knowledge and language.

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?

Opens with a specific verb+resource: "Write the instructions for an assistant," then enumerates the concrete platforms (custom GPT, Claude Project, Gemini Gem, Copilot agent, app system prompt) and the exact artifact set it returns. An agent can distinguish this from retrieval siblings like get_prompt or lint_prompts. It does not explicitly name or contrast those siblings, which keeps it short of a 5.

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?

Usage is only implied: you would call this when you need assistant instructions authored for one of the listed platforms. There is no statement of when not to use it and no routing to alternatives like get_prompt, get_prompt_pattern or grade_prompt, which occupy adjacent space. The prerequisite inputs (purpose, audience) are implicit in "From what it is for and who will use it," but not framed as guidance.

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