github_auto_link_pr_to_jira

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=true. The description adds useful context beyond those: the governed routing requirement, idempotency_key as a stable business-action identity, and the approval_ref/effect mechanism for resuming writes. However, it never explains what the destructiveHint=true means for this specific operation (linking a PR to Jira is not obviously destructive), and it doesn't describe what side effects occur. No direct contradiction with annotations, but the destructive flag is left unexplained.

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 two-line identification/routing preamble followed by a clean 7-line argument list. The governance constraint is front-loaded, and each line carries information. One small deduction because the opening line merely restates the tool name rather than adding substantive content.

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?

Despite annotations and an output schema being present, the description omits the core operational facts an agent needs: what auto-linking a PR to Jira does, what the connector 'arguments' JSON must contain (PR identifier, Jira issue key, etc.), and what the destructiveHint=true implies. For a generic wrapper with a nested arguments payload at 0% schema coverage, this is a significant gap — the agent cannot construct a correct call from the provided information.

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 description coverage is 0%, so the description must compensate — and it does provide a role label for all 7 parameters (e.g., project_id as 'Authenticated Project UUID', idempotency_key as 'Stable business-action identity'), giving the agent a conceptual grouping of governance-wrapper params. But several entries are vague or circular: 'arguments: JSON string of arguments for the connector operation' does not say what keys the JSON must contain for this operation, and 'project_ref: Exact project correlation reference' never defines what a correlation reference is or how to obtain it.

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 opens by restating the tool's name ('Github connector operation auto_link_pr_to_jira'), which is effectively a tautology. It never states what the operation actually accomplishes — e.g., that it creates a link between a GitHub pull request and a Jira issue. The only substantive sentence ('Routes only through the exact project/account governed connector authority') describes a routing constraint, not the tool's purpose, so an agent must infer the function entirely from the name.

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 select this tool over alternatives. The sibling list includes relevant GitHub and Jira tools (github_create_pull_request, github_merge_pull_request, jira_link_issues), but the description neither distinguishes itself nor states conditions for use. The routing sentence explains a constraint on execution, not when the agent should choose this tool.

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