add_labels

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description transparently reveals the critical behavior: the tool does not directly add labels but creates a request ('Request existing labels be added') and queues it for human approval. This corrects the potential false assumption from the tool name and is essential for proper use.

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 a single, well-structured sentence that front-loads the verb and resource, then immediately clarifies the approval queue aspect. Every word earns its place, with no redundancy or extraneous detail.

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 tool is relatively straightforward with 4 required parameters and an output schema present. The description covers the essential action, the key constraint (existing labels), and the approval-queue behavior. These details are sufficient for an agent to correctly select and invoke the tool, and since an output schema exists, return-value documentation is not necessary.

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?

With 0% schema description coverage, the description needs to compensate. It adds meaningful semantics for the 'labels' parameter by requiring 'existing labels' (i.e., not creating new ones) and references the 'issue' which maps to issue_number. However, it does not address the owner/repo parameters specifically, leaving some semantic burden on the agent's familiarity with GitHub APIs. Overall, partial compensation.

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 uses a specific verb 'Request' and clearly identifies the resource: 'existing labels be added to an issue'. It also explicitly distinguishes the tool from direct mutation by noting it 'queues exact action for human approval,' which sets it apart from siblings like 'add_issue_comment' or 'create_issue'.

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 conveys when to use this tool: when you want labels added to an issue. The phrase 'queues exact action for human approval' clearly implies that this tool is for requesting rather than directly executing, which indirectly tells the agent not to use it if immediate application is required. However, no explicit alternatives or exclusion conditions are stated.

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