update_thread_labels

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It reveals that label type IDs are used instead of label IDs, that removal resolves automatically, and non-existing types are ignored. However, it does not disclose side effects, permission requirements, or whether the operation is atomic or reversible, which leaves gaps for a mutation tool.

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 consists of two short sentences. The first states the core purpose clearly, and the second immediately provides essential usage details. There is no redundant or extraneous information, making it highly concise and well-structured for an agent to parse quickly.

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 the tool has 3 parameters, no output schema, and no annotations, the description adequately covers the core behavior: what the tool does, how parameters work, and an edge case (ignoring non-matching types). It could benefit from mentioning the return value (e.g., success response) or idempotency, but the essentials are present.

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?

The input schema provides 100% parameter descriptions, so the baseline is 3. The description adds meaningful context: it specifies that parameters take label TYPE IDs (not label IDs) from get_label_types, explains automatic resolution on removal, and clarifies that non-matching type IDs are ignored. This goes beyond the schema's simple 'Label type IDs' description.

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?

Description explicitly states 'Add and/or remove category labels on a thread in one call', clearly identifying the verb (add/remove) and resource (labels on a thread). This distinguishes it from the sibling tool 'add_labels' which only adds labels, making the purpose unique and unambiguous.

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 explains that both 'add' and 'remove' use label TYPE IDs from get_label_types, and that removal automatically resolves the type to the applied label. It also notes that type IDs not currently on the thread are ignored. However, it does not explicitly state when to use this tool versus alternatives like 'add_labels', though the combined add/remove functionality implies the use case.

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