Search everything

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

Annotations already indicate read-only and idempotent. The description adds that results include a relevance score and conversation id, and that the indexer may be disabled or catching up. This contextualizes the tool's behavior beyond the annotations.

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: first states core purpose, second provides usage and output context, third gives troubleshooting. Every sentence is valuable and front-loaded, with no wasted words.

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 description covers purpose, when to use vs alternatives, output structure, and error handling. It lacks parameter explanations, but the output schema exists and parameters are common. For a tool with 4 parameters and many siblings, this is nearly complete.

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 0%, so the description must compensate. It does not explain any of the 4 parameters (query, limit, offset, folder_id) beyond their schema names and defaults. The parameter names are self-explanatory but the description offers no additional guidance.

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 'Ranked full-corpus search across every indexed folder and account,' specifying the verb (search), resource (full-corpus), and scope. It distinguishes from siblings like mail_search and search_conversation, making the purpose unmistakable.

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?

Explicitly says 'Best for open questions' and provides examples. It also tells when not to use it: 'For precise filters... use mail_search instead.' Additionally, it advises calling search_index_status if results are empty, giving a complete usage roadmap.

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