github_delete_branch_ref

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

No contradiction with annotations: destructiveHint=true and readOnlyHint=false align with a delete operation. The description adds some useful context beyond the annotations — the governed-routing constraint and the write-approval flow ('effect: Claimed read or write effect; Spring verifies it', 'approval_ref: Approved platform task UUID when resuming a write'). However, it does not disclose what exactly gets destroyed, irreversibility, or failure modes for a destructive call.

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?

The description is compact and well-structured: a one-line identification header, a single routing sentence, and a labeled Args list. Each line is short and earns its place. It loses one point only because much of the content is generic connector boilerplate rather than tool-specific substance.

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 operation with zero schema description coverage and an opaque arguments JSON, the description is not complete enough to invoke correctly. The agent cannot construct the actual GitHub branch-ref deletion payload, does not learn the real-world effect, and gets no safety qualifiers about what deletion entails. The output schema covers return values, but the input side has a critical gap.

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 0%, so the description must compensate, and it does give one-line meanings for all 7 wrapper parameters (project_id, project_ref, connector_account_ref, idempotency_key, effect, approval_ref). However, the one parameter that carries the actual GitHub payload — 'arguments' — is described only as 'JSON string of arguments for the connector operation,' which is circular. An agent still does not know what fields (repo, ref, owner?) the JSON must contain, so the most important parameter remains opaque.

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 merely restates the tool name: 'Github connector operation delete_branch_ref (platform tool github.delete_branch_ref)'. It never explains in plain terms what deleting a branch ref does, what a branch ref is, or what the GitHub-side effect is. The routing sentence adds infrastructure context, not domain purpose, so this is effectively a tautology.

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?

No guidance is given on when to use this tool versus the many GitHub siblings (github_create_branch_ref, github_get_branch, github_list_branches, github_merge_pull_request). The only non-argument sentence, 'Routes only through the exact project/account governed connector authority,' is an infrastructure constraint, not a usage criterion. An agent cannot determine when deletion is appropriate or what to check first.

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