Search Emails

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

With no annotations provided, the description carries the burden of behavioral disclosure. It adds important behavior: results include all email fields so no follow-up get_email call is needed, and count_only=true returns only counts without the results array. These are valuable insights beyond the schema. It does not mention side effects, but as a search operation, this is acceptable.

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 efficiently structured in three short paragraphs, each earning its place: the main purpose, the key return-data insight, and the count_only use case. It is front-loaded with the primary action and avoids unnecessary fluff.

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?

For a search tool with 9 parameters and no output schema, the description covers essential context: what filters are available, that full data is returned, and how to get counts efficiently. Pagination and sorting are left to the schema, which already documents them. While it could mention pagination behavior, the description is sufficiently complete for informing tool selection and invocation.

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 high (89%), so the baseline is 3. The description adds value by highlighting the key filter dimensions (date range, user, contact) that map to parameters, and provides extra context for count_only beyond the schema description ('accurate counts on large datasets without returning the full result set'). This enriches the parameter understanding without duplicating every schema field.

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 'Search for logged emails with optional filters' with a specific verb and resource. It goes further to specify the filtering dimensions (date range, user, contact), distinguishing it from sibling search tools like search_notes and search_tasks. The statement about returning full data also differentiates it from get_email.

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 clear usage context, including when to use it ('find emails by date range, user, or contact') and a specific use case for count_only ('accurate counts on large datasets'). It also implies an alternative by stating 'no need to call get_email afterward.' However, it does not explicitly mention when not to use it or contrast with related tools like get_emails_attached_to_contact.

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