send_client_copy

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

The description discloses important behavioral traits beyond annotations: it preserves all client subjects, removes only internal reasoning, requires questions only when they block the next action, and enforces a 4096-character limit. It also clarifies that brevity is not achieved by fixed counts, which is non-obvious behavior. This complements the annotations (readOnlyHint=false, etc.) without contradiction.

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 long but every sentence serves a purpose: purpose, usage context, and specific formatting rules. It is front-loaded with the core purpose, followed by actionable guidelines. No word is wasted given the tool's complexity.

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, usage, content constraints, question policy, and the hard length limit. It references context ('client message or current project') and specifies Telegram. With an output schema available, return values need not be described. The tool is complex, but the description is thorough enough for an agent to select and invoke it correctly.

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?

The description provides rich semantics for the nested ClientTopic fields, explaining that titles must be concrete subjects, details should contain facts/proposals/actions, and questions have conditional rules. However, it does not address top-level parameters like project, subject, agent, model, route, or reference, leaving those to schema names. Given 0% schema description coverage, the partial compensation is strong but incomplete, warranting a 4.

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 opens with 'Send copy-ready text addressed directly to the client,' a specific verb+resource that clearly states the tool's function. It further distinguishes itself as 'the default tool when a manager should be able to copy the body without understanding the project or rewriting it,' separating it from siblings like send_update or send_text.

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 states when to use: 'when a manager should be able to copy the body without understanding the project or rewriting it.' This implies when not to use (when understanding/rewriting is needed). It also provides detailed content rules, such as requiring concrete topic titles and avoiding fixed report headings, guiding the agent on what to include and exclude.

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