Read GitHub stacks of pull requests

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

Annotations already declare read-only, idempotent and open-world, so the safety profile is covered. The description adds real behavioral context beyond that: bottom-to-top ordering with position 1 at the bottom, the null-not-error case, and the truncated flag signalling more matches than limit. The prompt-injection warning about titles is a useful extra safeguard.

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 concept, then method-by-method behavior, then naming rules and the trust boundary — a logical order with no filler. The long semicolon-chained sentences make it denser than ideal, but each clause carries information.

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 an output schema present, return-value structure is handled elsewhere, and the description still covers ordering, the null case, truncation, and defaults. Nothing an agent needs to select a method and supply arguments is missing.

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 already 100%, so the baseline is 3. The description goes further by explaining cross-parameter relationships the schema states only in isolation: naming a stack by its own number OR by a pull request within it, and that a bare number resolves against repo, meaning the working tree's origin.

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: 'Read GitHub native stacks, chains of pull requests where each is based on the head branch of the one below' defines the domain precisely, and it then splits the tool into two modes ("view" / "list"). This clearly distinguishes it from github_pr_read and the stack mutation siblings (github_stack_link/unlink).

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?

It explains what each method does and the defaults governing them (open-only unless state all, limit default 30), plus that naming by a pull request in no stack returns null rather than raising. It does not explicitly say when to prefer this over github_pr_read for pull-request details, which keeps it short of a 5.

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