hey_search

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

With no annotations, the description carries the burden. It discloses cache-first then network behavior, which is helpful. However, it does not disclose whether the search modifies any state (read-only assumed but not stated), nor what limitations apply (e.g., which email types are indexed).

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 short sentences, no redundant text. The main action leads, followed by an important usage note. Efficient and front-loaded.

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 no output schema and no annotations, the description is somewhat minimal. It lacks information about what is returned (e.g., full email objects vs. summaries), how pagination works, or rate limits. With many sibling tools, more context on search scope would help.

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 is 100% with descriptions. The description adds minor value by clarifying the purpose of force_refresh ('Bypass cache and search via network') but mostly restates the schema. It does not explain query syntax or expected format for the query parameter.

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 'Search emails by query' which identifies the primary action and resource. It distinguishes from sibling listing tools by implying general search across emails, but could be more explicit about the scope (e.g., all mailboxes).

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 the cache-first behavior and provides explicit guidance on using force_refresh for real-time results. However, it does not compare directly to sibling tools like hey_list_imbox or hey_list_feed to indicate when search is preferable over those specific lists.

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