Reply Compose

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, covering safety and idempotency. The description adds call ordering but introduces inconsistency in the mode list (schema has 'tone_shift', description has 'style'), reducing overall transparency.

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 concise at two sentences, with the first sentence focusing on purpose. However, the second sentence contains a misleading enumeration of modes that contradicts the schema, reducing its effectiveness.

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?

Despite an output schema existing, the description omits explanation of modes' behaviors, parameter roles, and return values. Given the tool's complexity (9 params), the description is too sparse to be 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?

With 9 parameters and 0% schema description coverage, the description should elaborate on parameter usage. It only lists a mismatched set of modes and fails to explain key parameters like message, style, citations, session_id, and others, providing almost no semantic value.

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 states 'Compose the final response for the user' which clearly indicates the tool's purpose. However, the listed modes (style, summary, format, nudge, repo_answer) do not match the input schema's enum (summarize, tone_shift), causing confusion about what modes are actually available.

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 instructs 'Call this LAST, after reasoning and judgment are complete,' providing clear usage order. However, it does not mention when not to use this tool or suggest alternatives among siblings.

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