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

Annotations already declare destructive=true and idempotent=false, so the safety profile is covered; the description adds real value on top by naming the default strategy (squash), disclosing that delete_branch removes the branch afterward, and stating the permission mode needed for main-branch merges. It stops short of saying whether the merge is reversible or what happens on conflicting/blocked PRs.

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 dense sentences, zero filler: the operation and its default come first, the side effect and permission caveat follow. Nothing repeats the tool name or annotations verbatim.

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 destructive, open-world mutation with no output schema and thin schema documentation, the description covers the operation, default, side effect, and authorization gate. It could be more complete about the return value (merge commit sha / result state) and about the unexplained 'title' parameter.

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 only 20%, so the description must carry weight: it does explain the 'method' enum, its default, and the semantics of 'delete_branch' ('removes its branch afterwards'). However, 'title' is left completely unexplained (presumably the commit message for squash/merge) and 'number' is undocumented in either place, leaving a meaningful gap.

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?

States a specific verb+resource ('Merge a pull request') and immediately enumerates the strategy space (squash by default, merge, rebase) plus the branch-deletion side effect. This distinguishes it cleanly from gh_pull_create and gh_pulls in the sibling list.

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?

Gives an explicit conditional prerequisite — merging into the main branch of a repo AskYourStack did not create requires the 'change anything' mode — and an explicit when-not: otherwise leave the merge to the user. An agent knows both when this is permitted and when to defer.

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