search_files

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

With no annotations, the description carries the full behavioral burden. It discloses the dialog-by-dialog scanning limitation, the 7-day default window, UTC timezone handling, and file_type exclusions such as voice/video notes. It does not mention limit/pagination behavior, but the core behavioral traits are transparent.

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 front-loaded with the core purpose and then organized into useful parameter details. It is somewhat long and the return-fields list is redundant with the output schema, but every paragraph earns its place and the caveats are meaningful.

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 the main invocation concerns: scope, file types, date semantics, and the global-search limitation. The query parameter meaning is not fully specified, which is the main gap; the output schema helps compensate for return-value expectations.

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 does so for file_type and since_date in detail, and for chat via the 'globally or in one chat' phrasing. Query and limit are left undocumented, but their names and defaults make them reasonably inferable.

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?

Opens with a specific verb and resource: 'Find messages carrying files, globally or in one chat.' This clearly differentiates from siblings like search_messages and download_file while matching the tool's name. The scope distinction is immediately clear.

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 when to use the tool ('globally or in one chat') and references the shared global-search caveat with search_messages. It does not explicitly tell the agent to use search_messages for text-only searches, but the context strongly implies the boundary.

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