gitlab_search_mrs

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

With no annotations, the description fully carries the burden. It explicitly states that the tool is read-only and that results are heuristic candidates, not guaranteed matches. This is a strong behavioral disclosure that manages expectations, though it could mention pagination or limit behavior.

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 very concise: two sentences with no wasted words. The key information (read-only, heuristic, search scope) is front-loaded, making it easy for the agent to quickly understand the tool's purpose.

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?

Given that an output schema exists (though not provided), the description need not detail return values. It covers purpose, scope, and caveats. Missing context includes what happens when no results are found or if the ticket key format is invalid, but these are minor omissions.

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 baseline is 3. The description adds minimal parameter-specific value beyond what the schema already provides (e.g., ticket_key example 'PROJ-123'). No new constraints or formatting details are introduced.

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 the verb ('find') and resource ('merge references') with a specific search scope (ticket key in MR title + description). It distinguishes from siblings like gitlab_get_mr (retrieves a specific MR) and gitlab_search_code (searches code) by focusing on ticket-linking heuristic.

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?

The description clarifies that the tool is read-only and heuristic, implying it should be used when exact linkage is not required. However, it does not explicitly exclude cases where a known MR ID is available or suggest gitlab_get_mr as an alternative, which would strengthen the guidance.

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