Create a saved search

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

Beyond annotations (which show no destructive or readOnly hints), the description discloses that nothing is copied or moved—just a stored query. It also explains online_search behavior (IMAP vs local), adding useful behavioral context that annotations lack.

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 concise with three paragraphs: purpose, parameter specifics, and a clarifying statement. Each sentence adds value, but the parameter explanation could be more compactly integrated.

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 8 parameters (3 required) and an output schema, the description covers the core functionality and key parameters. It lacks detail on some optional parameters, but overall it provides sufficient context for an agent to use the tool correctly.

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 0%, so the description must compensate. It explains search_folder_ids, terms, match_all, and online_search in detail, but omits confirm, dry_run_only, and parent_folder_id. This partial coverage justifies a 3.

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 creates a saved search that appears in the folder pane, distinguishing it from other search tools like mail_search or search_global. It specifies that it's a stored query, not a copy/move, which helps an agent understand the unique function.

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 provides usage context, such as search_folder_ids from folder_list and terms syntax with attributes/operators. It explains when to use it (persistent search) but does not explicitly state when not to use it or mention alternatives; however, the context of sibling tools and the term 'saved search' implicitly differentiates.

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