generate_pr

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

Despite annotations being minimal (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description adds rich behavioral context: atomic all-or-nothing commit, refusal of conflicts and invalid AST, draft-only creation, no auto-merge, and token requirement. No contradiction with annotations.

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?

Description is dense but well-structured, starting with main purpose and then detailing constraints and inputs. Some redundancy could be trimmed, but it's efficient overall.

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?

Covers purpose, guidelines, behavior, parameter context adequately. Given presence of output schema, description focuses on inputs and behavior. Minor omission: error handling beyond CONFLICT and AST_INVALID, but not critical.

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 description adds supplementary context: patches come from suggest_fix, local_only as fallback without token. This adds value beyond schema definitions.

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 it opens a draft GitHub PR with a11y patches applied atomically via Git Trees, distinguishing it from siblings like suggest_fix and generate_patch. It specifies it always creates draft PRs and never auto-merges.

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?

Explicitly states when to use (with patches from suggest_fix, preferred) and alternatives (generate_patch is legacy). Provides conditions: requires GITHUB_TOKEN; otherwise set local_only=true. Also mentions it refuses overlapping patches and unparseable files.

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