update_label

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

Annotations only include openWorldHint=true, which is low-signal for behavior. The description compensates by disclosing that the tool changes remote GitLab state, requires permissions, and that GitLab returns validation/conflict/permission/rate-limit errors instead of silently applying invalid requests. This adds behavioral context beyond the annotation. A small deduction for not detailing reversibility or partial updates, but it covers the main operational safety and error 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 three sentences, tightly packed with essential operational details: what it updates, when to use it, permissions, error behavior, and parameter conventions. No redundancy, and the key purpose is front-loaded. Every sentence adds value.

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 mutation tool with 6 parameters and no output schema, the description covers usage boundaries, permissions, error responses, and parameter conventions. It lacks details on the response format (which the output schema would otherwise provide) and doesn't describe the return behavior of the updated label, but given the absence of an output schema, the error-handling and permission guidance are strong. A 4 is justified since a tool this complex could benefit from a note on side effects or idempotency, but the core agent needs are met.

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 100%, so the schema already documents all parameters. The description adds the distinction between accepting numeric ID or URL-encoded path for project_id/group_id, and warns to use required identifiers and pagination fields exactly as documented. This adds a small layer of semantic guidance on top of the schema, but most meaning is already in the schema. Baseline 3, with a bump for the ID/path and pagination note.

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 states a specific verb ('Update') and resource ('an existing label in a project'), which distinguishes it clearly from sibling tools like create_label and delete_label. It also clarifies the difference between labels and notes, which helps select the right tool among similar update/create/delete siblings.

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?

Provides explicit guidance on when to use this tool: for an existing resource, choosing the create tool for new resources and a note tool for discussion-only text. It also mentions permission requirements and how GitLab returns errors, which informs the agent when to expect failure. This is explicit when/when-not guidance.

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