send_file

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

Annotations already signal non-read-only, external side effects (openWorldHint), and non-idempotent behavior. The description adds valuable context: allowed_roots path restriction, the auto/non-auto mode selection, and the 1024-character caption limit. No contradiction with 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 concise sentences, front-loads the primary purpose, and packs essential constraints (allowed roots, kind behavior, caption limits) without fluff. Every sentence earns its place.

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 the high complexity (10 parameters, 6 required) and rich output schema, the description covers key behavioral rules but misses important required parameter semantics and does not fully explain conditions or edge cases. It is more complete than average but still has clear gaps.

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 'path', 'kind', 'caption', and 'format', but leaves required parameters 'project', 'subject', 'agent', 'model', and optional 'route'/'reference' completely undocumented. This is inadequate for a 10-parameter tool.

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 sends an explicitly requested local file or image with a caption, which is a specific verb+resource+scope. It distinguishes itself from sibling tools like send_text and send_update by focusing on files/images rather than text messages or status updates.

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: files must resolve under files.allowed_roots, kind=auto behavior is explained, and caption format/length limits are given. It does not explicitly name alternatives or when not to use, but the 'explicitly requested' phrasing implies appropriate conditions.

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