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

Annotations already mark it as read-only (readOnlyHint: true). The description adds value by specifying the output content (statuses and approval counts) and the prerequisite 'Requires project context,' which is behavioral context beyond the annotation. It does not describe pagination or error cases, but for a simple read-only list, the disclosure is adequate and does not contradict 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?

Two sentences, front-loaded with the primary action and output details, followed by the prerequisite. No redundant phrasing or fluff. Every sentence contributes essential information.

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?

The description covers the returned data and the project-context requirement, which are the key details an agent needs to call it correctly. It lacks explicit mention of pagination, ordering, or default behavior, but for a simple read-only list operation with one parameter and no output schema, the coverage is adequate. It could have explicitly noted that it lists all merge requests for the given spec without any filtering, but that is reasonably implied.

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 for the single parameter (specId) is 100%, and the schema already describes it as 'Public ID (GUID) of the API specification.' The description does not add additional meaning about the parameter beyond referencing 'a spec.' It neither clarifies format nor provides examples, so it stays at the baseline for well-documented schemas.

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 tool lists merge requests for a given spec, specifies the returned status values, and mentions the approval count. The verb 'list' and resource 'merge requests' are specific, and the scope 'of a spec' distinguishes it from generic list tools and the singular get_merge_request.

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 notes 'Requires project context,' which is a clear prerequisite and hints that the tool operates within a set project scope. It does not explicitly name alternatives or when not to use it, but the sibling get_merge_request exists and the description implies this is the plural listing counterpart. It gives enough context to know when to call it, though it could be more explicit about alternatives.

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